mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-23 12:12:39 +08:00
103 KiB
103 KiB
| 1 | test_case | gpu | gpu_mem_total | gpu_mem_peak | host_mem_peak | host_subprocess | host_subprocess_duration | gpu_subprocess | gpu_subprocess_duration | concurrent_gpu_proc_count | pid | unittest_case_name | stage_duration | build_id | duration | stage_only | test_stage | gpu_factor | host_factor | parallel_factor | parent_case | gpu_is_fractional_sum | gpu_is_fractional_count |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | test_unittests[quantization] | NVIDIA A10 | 23028 | 1148 | 5357 | {'1914323': 125.0078125, '1916110': 10.296875, '1916302': 20.81640625, '1916111': 21.88671875, '1916303': 30.71875, '1916408': 5158.00390625, '1916540': 11.69921875} | {'1914323': 487.81, '1916110': 487.81, '1916302': 0.0, '1916111': 487.81, '1916303': 487.31, '1916408': 486.31, '1916540': 481.81} | {'1916408': 1148.0} | {'1916408': 479.3} | 1 | 1914323 | quantization | 2601.935 | 16148 | 488.1039742 | A10-functional-0 | [A10-functional-0] Run TURTLE | 20.05923345 | 18.35056935 | 18 | test_unittests[quantization] | 0 | 160 |
| 3 | test_unittests[model-gptj] | NVIDIA A10 | 23028 | 4262 | 7020 | {'1914323': 124.01171875, '1916110': 10.40625, '1937094': 25.7109375, '1916111': 21.8984375, '1937097': 28.08984375, '1937099': 6824.375, '1937292': 11.69921875} | {'1914323': 150.1, '1916110': 150.1, '1937094': 0.0, '1916111': 150.1, '1937097': 149.1, '1937099': 149.1, '1937292': 144.6} | {'1937099': 4262.0} | {'1937099': 134.5} | 1 | 1914323 | model-gptj | 2601.935 | 16148 | 150.4665946 | A10-functional-0 | [A10-functional-0] Run TURTLE | 5.403097137 | 14.0034188 | 5 | test_unittests[model-gptj] | 0 | 7 |
| 4 | test_unittests[functional] | NVIDIA A10 | 23028 | 3826 | 7503 | {'1914323': 124.484375, '1916110': 10.55078125, '1958270': 18.8671875, '1916111': 21.90234375, '1958271': 34.16015625, '1958273': 7300.71875, '1958409': 12.46875} | {'1914323': 1571.47, '1916110': 1571.47, '1958270': 0.0, '1916111': 1571.47, '1958271': 1570.97, '1958273': 1570.47, '1958409': 1566.46} | {'1958273': 3826.0} | {'1958273': 1564.46} | 1 | 1914323 | functional | 2601.935 | 16148 | 1572.05029 | A10-functional-0 | [A10-functional-0] Run TURTLE | 6.01881861 | 13.10195922 | 6 | test_unittests[functional] | 0 | 584 |
| 5 | test_unittests[model-gptneox] | NVIDIA A10 | 23028 | 7778 | 10464 | {'4024936': 10.35546875, '4024953': 22.0234375, '4011642': 131.34375, '4073424': 25.875, '4073425': 29.6171875, '4073429': 10263.78125, '4073584': 14.140625} | {'4024936': 232.2, '4024953': 232.2, '4011642': 232.2, '4073424': 0.0, '4073425': 231.7, '4073429': 231.2, '4073584': 227.19} | {'4073429': 7778.0} | {'4073429': 205.18} | 1 | 4011642 | model-gptneox | 1840.245 | 16148 | 232.9099628 | A10-accuracy-1 | [A10-accuracy-1] Run TURTLE | 2.960658267 | 9.394495413 | 2 | test_unittests[model-gptneox] | 0 | 6 |
| 6 | test_unittests[attention-bert] | NVIDIA A10 | 23028 | 1348 | 5377 | {'4024936': 10.5, '4024953': 22.0234375, '4011642': 132.48828125, '4078474': 14.89453125, '4078499': 29.84765625, '4078501': 5177.5625, '4078574': 14.203125} | {'4024936': 194.16, '4024953': 194.16, '4011642': 194.16, '4078474': 0.0, '4078499': 193.66, '4078501': 192.66, '4078574': 188.65} | {'4078501': 1348.0} | {'4078501': 186.65} | 1 | 4011642 | attention-bert | 1840.245 | 16148 | 194.3609619 | A10-accuracy-1 | [A10-accuracy-1] Run TURTLE | 17.08308605 | 18.28231356 | 17 | test_unittests[attention-bert] | 0 | 49 |
| 7 | test_unittests[model-falcon] | NVIDIA A10 | 23028 | 904 | 5881 | {'191640': 10.27734375, '191667': 21.953125, '113110': 136.4609375, '250567': 12.765625, '250570': 29.546875, '250650': 5671.984375, '250819': 11.7265625} | {'191640': 79.58, '191667': 79.58, '113110': 79.58, '250567': 0.0, '250570': 79.08, '250650': 78.08, '250819': 74.07} | {'250650': 904.0} | {'250650': 72.07} | 1 | 113110 | model-falcon | 2398.758 | 16148 | 79.83350172 | A10-e2e-0 | [A10-e2e-0] Run TURTLE | 25.47345133 | 16.71552457 | 16 | test_unittests[model-falcon] | 0 | 12 |
| 8 | test_unittests[model-gpt-partition2] | NVIDIA A10 | 23028 | 1530 | 8682 | {'3034787': 125.1953125, '3040198': 21.98046875, '3040195': 10.375, '3040511': 21.43359375, '3040551': 30.03125, '3040638': 8483.87890625, '3041086': 14.265625} | {'3034787': 1580.7, '3040198': 1580.7, '3040195': 1580.7, '3040511': 0.0, '3040551': 1579.7, '3040638': 1578.69, '3041086': 1574.19} | {'3040638': 1530.0} | {'3040638': 1571.61} | 1 | 3034787 | model-gpt-partition2 | 3425.112 | 16148 | 1580.727964 | A10-model-5 | [A10-model-5] Run TURTLE | 15.05098039 | 11.3227367 | 11 | test_unittests[model-gpt-partition2] | 0 | 96 |
| 9 | test_unittests[model-gpt-partition3] | NVIDIA A10 | 23028 | 1534 | 8478 | {'3104960': 17.3671875, '3034787': 128.60546875, '3040198': 22.0390625, '3040195': 10.46484375, '3104962': 29.01171875, '3104966': 8280.40234375, '3105095': 14.17578125} | {'3104960': 0.0, '3034787': 1674.9, '3040198': 1674.9, '3040195': 1674.9, '3104962': 1674.4, '3104966': 1673.9, '3105095': 1668.89} | {'3104966': 1534.0} | {'3104966': 1666.39} | 1 | 3034787 | model-gpt-partition3 | 3425.112 | 16148 | 1675.346662 | A10-model-5 | [A10-model-5] Run TURTLE | 15.01173403 | 11.59518754 | 11 | test_unittests[model-gpt-partition3] | 0 | 96 |
| 10 | test_unittests[model-gpt-other] | NVIDIA A10 | 23028 | 1726 | 5650 | {'3366561': 23.39453125, '3034787': 124.37109375, '3040198': 21.99609375, '3040195': 10.46875, '3367496': 29.06640625, '3368364': 5453.6953125, '3377978': 14.15625} | {'3366561': 0.0, '3034787': 95.63, '3040198': 95.63, '3040195': 95.63, '3367496': 95.13, '3368364': 94.63, '3377978': 90.63} | {'3368364': 1726.0} | {'3368364': 86.63} | 1 | 3034787 | model-gpt-other | 3425.112 | 16148 | 95.92389283 | A10-model-5 | [A10-model-5] Run TURTLE | 13.34183082 | 17.39893805 | 13 | test_unittests[model-gpt-other] | 0 | 4 |
| 11 | test_unittests[attention-gpt-plugin-ib-mode] | NVIDIA A10 | 23028 | 1168 | 5473 | {'200024': 21.89453125, '193493': 124.91796875, '200023': 10.26171875, '200281': 23.71875, '200282': 31.34765625, '200417': 5274.41015625, '200650': 11.6328125} | {'200024': 140.93, '193493': 140.93, '200023': 140.93, '200281': 0.0, '200282': 139.93, '200417': 138.92, '200650': 134.42} | {'200417': 1168.0} | {'200417': 132.42} | 1 | 193493 | attention-gpt-plugin-ib-mode | 975.712 | 16148 | 141.0570997 | A10-accuracy-2 | [A10-accuracy-2] Run TURTLE | 19.71575342 | 17.96162982 | 17 | test_unittests[attention-gpt-plugin-ib-mode] | 0 | 34 |
| 12 | test_unittests[attention-gpt-no-cache] | NVIDIA A10 | 23028 | 690 | 4255 | {'200024': 21.8984375, '211633': 11.6015625, '193493': 123.97265625, '200023': 10.38671875, '211636': 28.25390625, '211639': 4059.72265625, '211821': 11.69921875} | {'200024': 19.06, '211633': 0.0, '193493': 19.06, '200023': 19.06, '211636': 18.55, '211639': 18.05, '211821': 13.51} | {'211639': 690.0} | {'211639': 11.51} | 1 | 193493 | attention-gpt-no-cache | 975.712 | 16148 | 19.44269817 | A10-accuracy-2 | [A10-accuracy-2] Run TURTLE | 33.37391304 | 23.10317274 | 23 | test_unittests[attention-gpt-no-cache] | 0 | 2 |
| 13 | test_unittests[model-mamba] | NVIDIA A10 | 23028 | 776 | 7856 | {'200024': 21.94140625, '244112': 22.6484375, '193493': 124.70703125, '200023': 10.4296875, '244115': 45.91796875, '244120': 23.72265625, '244192': 28.19921875, '244197': 7659.5859375, '244385': 12.484375} | {'200024': 362.64, '244112': 0.0, '193493': 362.64, '200023': 362.64, '244115': 1.0, '244120': 0.0, '244192': 360.14, '244197': 359.64, '244385': 355.63} | {'244197': 776.0} | {'244197': 291.72} | 1 | 193493 | model-mamba | 975.712 | 16148 | 363.0035413 | A10-accuracy-2 | [A10-accuracy-2] Run TURTLE | 29.67525773 | 12.51323829 | 12 | test_unittests[model-mamba] | 0 | 12 |
| 14 | test_unittests[model-llama] | NVIDIA A10 | 23028 | 782 | 31452 | {'2850601': 132.15234375, '2852074': 21.94921875, '2852073': 10.421875, '2852215': 29.9921875, '2852295': 31251.640625, '2852374': 12.44140625} | {'2850601': 2166.4, '2852074': 2166.4, '2852073': 2166.4, '2852215': 2165.9, '2852295': 2164.89, '2852374': 2160.89} | {'2852295': 782.0} | {'2852295': 2158.89} | 1 | 2850601 | model-llama | 2222.033 | 16148 | 2166.631013 | A10-e2e-2 | [A10-e2e-2] Run TURTLE | 29.44757033 | 3.125524609 | 3 | test_unittests[model-llama] | 0 | 56 |
| 15 | test_unittests[attention-gpt-partition0] | NVIDIA A10 | 23028 | 1514 | 6725 | {'4076739': 126.00390625, '4079125': 10.26953125, '4079126': 21.94921875, '4079321': 23.5625, '4079322': 29.75390625, '4079335': 6526.16796875, '4079659': 11.69921875} | {'4076739': 205.44, '4079125': 205.44, '4079126': 205.44, '4079321': 0.0, '4079322': 204.44, '4079335': 203.94, '4079659': 199.44} | {'4079335': 1514.0} | {'4079335': 196.43} | 1 | 4076739 | attention-gpt-partition0 | 2895.903 | 16148 | 205.6961429 | A10-unittests | [A10-unittests] Run TURTLE | 15.21003963 | 14.61769517 | 14 | test_unittests[attention-gpt-partition0] | 0 | 60 |
| 16 | test_unittests[attention-gpt-partition1] | NVIDIA A10 | 23028 | 2114 | 6678 | {'4094656': 20.15625, '4076739': 126.0078125, '4079125': 10.41796875, '4079126': 21.953125, '4094661': 28.88671875, '4094664': 6479.94140625, '4094767': 11.7265625} | {'4094656': 0.0, '4076739': 212.86, '4079125': 212.86, '4079126': 212.86, '4094661': 212.36, '4094664': 211.36, '4094767': 206.86} | {'4094664': 2114.0} | {'4094664': 203.86} | 1 | 4076739 | attention-gpt-partition1 | 2895.903 | 16148 | 213.0989715 | A10-unittests | [A10-unittests] Run TURTLE | 10.89309366 | 14.72057502 | 10 | test_unittests[attention-gpt-partition1] | 0 | 60 |
| 17 | test_unittests[attention-gpt-partition2] | NVIDIA A10 | 23028 | 7204 | 6664 | {'4076739': 126.0078125, '4079125': 10.42578125, '4079126': 21.95703125, '4110083': 29.015625, '4110123': 6465.88671875, '4110375': 11.69921875} | {'4076739': 213.72, '4079125': 213.72, '4079126': 213.72, '4110083': 213.22, '4110123': 212.72, '4110375': 208.22} | {'4110123': 7204.0} | {'4110123': 204.21} | 1 | 4076739 | attention-gpt-partition2 | 2895.903 | 16148 | 214.206686 | A10-unittests | [A10-unittests] Run TURTLE | 3.196557468 | 14.7515006 | 3 | test_unittests[attention-gpt-partition2] | 0 | 63 |
| 18 | test_unittests[attention-gpt-partition3] | NVIDIA A10 | 23028 | 7210 | 6784 | {'4076739': 126.0078125, '4079125': 10.44140625, '4079126': 21.95703125, '4125693': 28.7421875, '4125695': 6585.41796875, '4125878': 11.69921875} | {'4076739': 218.51, '4079125': 218.51, '4079126': 218.51, '4125693': 218.01, '4125695': 218.01, '4125878': 213.01} | {'4125695': 7210.0} | {'4125695': 209.0} | 1 | 4076739 | attention-gpt-partition3 | 2895.903 | 16148 | 219.2195411 | A10-unittests | [A10-unittests] Run TURTLE | 3.193897365 | 14.49056604 | 3 | test_unittests[attention-gpt-partition3] | 0 | 62 |
| 19 | test_unittests[attention-gpt-xqa-generic] | NVIDIA A10 | 23028 | 11482 | 8546 | {'4076739': 126.11328125, '4143236': 23.703125, '4079125': 10.4765625, '4079126': 21.984375, '4143304': 33.26953125, '4143371': 8342.43359375, '4143805': 14.3125} | {'4076739': 1973.34, '4143236': 0.0, '4079125': 1973.34, '4079126': 1973.34, '4143304': 1972.84, '4143371': 1972.34, '4143805': 1967.84} | {'4143371': 11482.0} | {'4143371': 1965.83} | 1 | 4076739 | attention-gpt-xqa-generic | 2895.903 | 16148 | 1973.925239 | A10-unittests | [A10-unittests] Run TURTLE | 2.005573942 | 11.50292535 | 2 | test_unittests[attention-gpt-xqa-generic] | 0 | 428 |
| 20 | test_unittests[model-gpt-partition0] | NVIDIA A30 | 24576 | 1270 | 7472 | {'2310400': 125.5390625, '2317659': 16.3046875, '2317198': 21.95703125, '2317183': 10.28125, '2317790': 29.93359375, '2317877': 7273.1015625, '2318739': 11.703125} | {'2310400': 1501.65, '2317659': 0.0, '2317198': 1501.65, '2317183': 1501.65, '2317790': 1501.15, '2317877': 1500.15, '2318739': 1495.65} | {'2317877': 1270.0} | {'2317877': 1493.14} | 1 | 2310400 | model-gpt-partition0 | 4675.14 | 16148 | 1502.245237 | A30-model-4 | [A30-model-4] Run TURTLE | 19.3511811 | 13.15631692 | 13 | test_unittests[model-gpt-partition0] | 0 | 96 |
| 21 | test_unittests[model-gpt-partition1] | NVIDIA A30 | 24576 | 1240 | 7495 | {'2310400': 125.54296875, '2317198': 21.9765625, '2317183': 10.41015625, '2414382': 28.89453125, '2414449': 7297.3125, '2414597': 11.70703125} | {'2310400': 1455.04, '2317198': 1455.04, '2317183': 1455.04, '2414382': 1454.54, '2414449': 1454.04, '2414597': 1450.03} | {'2414449': 1240.0} | {'2414449': 1447.03} | 1 | 2310400 | model-gpt-partition1 | 4675.14 | 16148 | 1455.407928 | A30-model-4 | [A30-model-4] Run TURTLE | 19.81935484 | 13.11594396 | 13 | test_unittests[model-gpt-partition1] | 0 | 96 |
| 22 | test_unittests[model-gpt-partition2] | NVIDIA A30 | 24576 | 1240 | 7495 | {'2310400': 125.54296875, '2317198': 21.9765625, '2317183': 10.41015625, '2414382': 28.89453125, '2414449': 7297.3125, '2414597': 11.70703125} | {'2310400': 1455.04, '2317198': 1455.04, '2317183': 1455.04, '2414382': 1454.54, '2414449': 1454.04, '2414597': 1450.03} | {'2414449': 1240.0} | {'2414449': 1447.03} | 1 | 2310400 | model-gpt-partition2 | 4675.14 | 16148 | 1455.407928 | A30-model-4 | [A30-model-4] Run TURTLE | 19.81935484 | 13.11594396 | 4 | test_unittests[model-gpt-partition2] | 0 | 96 |
| 23 | test_unittests[model-gpt-partition3] | NVIDIA A30 | 24576 | 1240 | 7495 | {'2310400': 125.54296875, '2317198': 21.9765625, '2317183': 10.41015625, '2414382': 28.89453125, '2414449': 7297.3125, '2414597': 11.70703125} | {'2310400': 1455.04, '2317198': 1455.04, '2317183': 1455.04, '2414382': 1454.54, '2414449': 1454.04, '2414597': 1450.03} | {'2414449': 1240.0} | {'2414449': 1447.03} | 1 | 2310400 | model-gpt-partition3 | 4675.14 | 16148 | 1455.407928 | A30-model-4 | [A30-model-4] Run TURTLE | 19.81935484 | 13.11594396 | 4 | test_unittests[model-gpt-partition3] | 0 | 96 |
| 24 | test_unittests[others] | NVIDIA A30 | 24576 | 23160 | 34499 | {'2874872': 21.97265625, '2871492': 128.36328125, '2874871': 10.36328125, '2875050': 24.50390625, '2875089': 39.65234375, '2875095': 34301.00390625, '2875320': 19.66796875, '2970097': 391.2578125, '2970098': 391.09765625, '2970099': 390.140625, '2970100': 389.80859375, '2970391': 11.80078125, '2970408': 387.70703125, '2970409': 387.31640625, '2970410': 387.42578125, '2970411': 387.16015625} | {'2874872': 3133.71, '2871492': 3133.71, '2874871': 3133.71, '2875050': 0.0, '2875089': 3132.71, '2875095': 3132.21, '2875320': 3126.67, '2970097': 4.5, '2970098': 4.5, '2970099': 4.5, '2970100': 4.5, '2970391': 9.5, '2970408': 9.0, '2970409': 9.0, '2970410': 9.0, '2970411': 9.0} | {'2875095': 23160.0} | {'2875095': 3125.16} | 1 | 2871492 | others | 8798.348 | 16148 | 3133.753364 | A30-others-2 | [A30-others-2] Run TURTLE | 1.061139896 | 2.849473898 | 1 | test_unittests[others] | 10 | 744 |
| 25 | test_unittests[llmapi-models-part1] | NVIDIA A30 | 24576 | 23350 | 50581 | {'2874872': 22.07421875, '2871492': 127.7265625, '3044856': 23.71484375, '2874871': 10.6953125, '3044857': 29.72265625, '3044861': 50382.52734375, '3044974': 14.08203125, '3706076': 58.5, '3884726': 46.9296875} | {'2874872': 2243.64, '2871492': 2243.64, '3044856': 0.0, '2874871': 2243.64, '3044857': 2243.14, '3044861': 2242.14, '3044974': 2237.64, '3706076': 8.0, '3884726': 1.5} | {'3044861': 23350.0} | {'3044861': 2133.29} | 1 | 2871492 | llmapi-models-part1 | 8798.348 | 16148 | 2243.90992 | A30-others-2 | [A30-others-2] Run TURTLE | 1.052505353 | 1.94349657 | 1 | test_unittests[llmapi-models-part1] | 3 | 11 |
| 26 | test_unittests[llmapi-models-part2] | NVIDIA A30 | 24576 | 18636 | 78798 | {'2874872': 22.09375, '2871492': 127.80078125, '2874871': 10.75390625, '3964775': 78598.30859375, '3964722': 28.6015625, '3965217': 14.1015625} | {'2874872': 1953.28, '2871492': 1953.28, '2874871': 1953.28, '3964775': 1952.78, '3964722': 1952.78, '3965217': 1947.78} | {'3964775': 18636.0} | {'3964775': 1935.77} | 1 | 2871492 | llmapi-models-part2 | 8798.348 | 16148 | 1953.9569 | A30-others-2 | [A30-others-2] Run TURTLE | 1.318737927 | 1.247544354 | 1 | test_unittests[llmapi-models-part2] | 2 | 9 |
| 27 | test_unittests[llmapi-models-part3] | NVIDIA A30 | 24576 | 15428 | 53868 | {'2874872': 22.1171875, '2871492': 131.4296875, '4095109': 24.49609375, '2874871': 10.80078125, '4095110': 28.5078125, '4095112': 53668.12890625, '4095235': 14.1328125, '4100024': 116.00390625, '4100294': 20.890625} | {'2874872': 1409.05, '2871492': 1409.05, '4095109': 0.0, '2874871': 1409.05, '4095110': 1408.55, '4095112': 1408.05, '4095235': 1404.04, '4100024': 17.01, '4100294': 0.0} | {'4095112': 15428.0} | {'4095112': 1394.15} | 1 | 2871492 | llmapi-models-part3 | 8798.348 | 16148 | 1409.584443 | A30-others-2 | [A30-others-2] Run TURTLE | 1.592947887 | 1.824905324 | 1 | test_unittests[llmapi-models-part3] | 1 | 6 |
| 28 | test_unittests[others] | NVIDIA A100X | 81559 | 73756 | 27628 | {'3215898': 10.3359375, '3215933': 21.49609375, '3213061': 130.5, '3323042': 30.0546875, '3323055': 12172.48828125, '3323325': 29.2265625, '3323842': 8266.75390625, '3323843': 8935.0859375, '3326674': 2611.1953125, '3326675': 2611.8046875, '3326906': 2605.125, '3326905': 2607.7578125, '3327221': 2596.72265625, '3327222': 2596.32421875, '3329303': 8834.60546875, '3329304': 8454.85546875, '3332276': 8050.3359375, '3332277': 9001.72265625, '3334107': 8570.27734375, '3334108': 8940.27734375, '3337392': 8802.87109375, '3337393': 9091.703125, '3340439': 8662.23046875, '3340440': 8963.91796875, '3343414': 8724.72265625, '3343415': 8828.78515625, '3346319': 11.6875, '3346336': 0.3828125, '3346337': 0.37890625, '3346360': 2604.953125, '3346366': 2609.21875, '3346776': 8781.49609375, '3346780': 8883.0} | {'3215898': 420.74, '3215933': 420.74, '3213061': 420.74, '3323042': 420.24, '3323055': 419.74, '3323325': 414.73, '3323842': 40.53, '3323843': 41.53, '3326674': 7.51, '3326675': 7.51, '3326906': 9.51, '3326905': 9.51, '3327221': 7.51, '3327222': 7.51, '3329303': 43.02, '3329304': 43.02, '3332276': 49.03, '3332277': 49.03, '3334107': 45.52, '3334108': 46.02, '3337392': 36.52, '3337393': 37.02, '3340439': 45.52, '3340440': 46.52, '3343414': 37.02, '3343415': 37.52, '3346319': 12.01, '3346336': 11.51, '3346337': 11.51, '3346360': 11.51, '3346366': 11.51, '3346776': 45.02, '3346780': 45.02} | {'3323842': 3074.0, '3323843': 610.0, '3326674': 73454.0, '3326905': 34118.0, '3327221': 34118.0, '3323055': 4062.0, '3329303': 34332.0, '3329304': 896.0, '3332276': 33510.0, '3332277': 608.0, '3334107': 72426.0, '3334108': 896.0, '3337392': 72432.0, '3337393': 896.0, '3340439': 72422.0, '3340440': 896.0, '3343414': 72492.0, '3343415': 608.0, '3346360': 72858.0, '3346776': 34398.0, '3346780': 610.0} | {'3323842': 35.52, '3323843': 23.01, '3326674': 3.5, '3326905': 4.5, '3327221': 4.0, '3323055': 347.68, '3329303': 38.02, '3329304': 24.01, '3332276': 44.52, '3332277': 35.52, '3334107': 40.02, '3334108': 26.01, '3337392': 32.01, '3337393': 21.01, '3340439': 40.02, '3340440': 26.01, '3343414': 32.51, '3343415': 21.01, '3346360': 4.0, '3346776': 40.52, '3346780': 27.51} | 3 | 3213061 | others | 5543.396 | 16148 | 421.1721736 | A100X-3 | [A100X-3] Run TURTLE | 1.105794783 | 3.558129434 | 4 | test_unittests[others] | 6 | 13 |
| 29 | test_unittests[llmapi-tp-2gpu] | NVIDIA H100 80GB HBM3 | 81559 | 73756 | 27628 | {'3215898': 10.3359375, '3215933': 21.49609375, '3213061': 130.5, '3323042': 30.0546875, '3323055': 12172.48828125, '3323325': 29.2265625, '3323842': 8266.75390625, '3323843': 8935.0859375, '3326674': 2611.1953125, '3326675': 2611.8046875, '3326906': 2605.125, '3326905': 2607.7578125, '3327221': 2596.72265625, '3327222': 2596.32421875, '3329303': 8834.60546875, '3329304': 8454.85546875, '3332276': 8050.3359375, '3332277': 9001.72265625, '3334107': 8570.27734375, '3334108': 8940.27734375, '3337392': 8802.87109375, '3337393': 9091.703125, '3340439': 8662.23046875, '3340440': 8963.91796875, '3343414': 8724.72265625, '3343415': 8828.78515625, '3346319': 11.6875, '3346336': 0.3828125, '3346337': 0.37890625, '3346360': 2604.953125, '3346366': 2609.21875, '3346776': 8781.49609375, '3346780': 8883.0} | {'3215898': 420.74, '3215933': 420.74, '3213061': 420.74, '3323042': 420.24, '3323055': 419.74, '3323325': 414.73, '3323842': 40.53, '3323843': 41.53, '3326674': 7.51, '3326675': 7.51, '3326906': 9.51, '3326905': 9.51, '3327221': 7.51, '3327222': 7.51, '3329303': 43.02, '3329304': 43.02, '3332276': 49.03, '3332277': 49.03, '3334107': 45.52, '3334108': 46.02, '3337392': 36.52, '3337393': 37.02, '3340439': 45.52, '3340440': 46.52, '3343414': 37.02, '3343415': 37.52, '3346319': 12.01, '3346336': 11.51, '3346337': 11.51, '3346360': 11.51, '3346366': 11.51, '3346776': 45.02, '3346780': 45.02} | {'3323842': 3074.0, '3323843': 610.0, '3326674': 73454.0, '3326905': 34118.0, '3327221': 34118.0, '3323055': 4062.0, '3329303': 34332.0, '3329304': 896.0, '3332276': 33510.0, '3332277': 608.0, '3334107': 72426.0, '3334108': 896.0, '3337392': 72432.0, '3337393': 896.0, '3340439': 72422.0, '3340440': 896.0, '3343414': 72492.0, '3343415': 608.0, '3346360': 72858.0, '3346776': 34398.0, '3346780': 610.0} | {'3323842': 35.52, '3323843': 23.01, '3326674': 3.5, '3326905': 4.5, '3327221': 4.0, '3323055': 347.68, '3329303': 38.02, '3329304': 24.01, '3332276': 44.52, '3332277': 35.52, '3334107': 40.02, '3334108': 26.01, '3337392': 32.01, '3337393': 21.01, '3340439': 40.02, '3340440': 26.01, '3343414': 32.51, '3343415': 21.01, '3346360': 4.0, '3346776': 40.52, '3346780': 27.51} | 3 | 3213061 | llmapi-tp-2gpu | 5543.396 | 16148 | 421.1721736 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.105794783 | 3.558129434 | 1 | test_unittests[llmapi-tp-2gpu] | 6 | 13 |
| 30 | test_unittests[llmapi-models-2gpu] | NVIDIA H100 80GB HBM3 | 81559 | 74276 | 73436 | {'3215898': 10.44140625, '3215933': 21.50390625, '3213061': 127.8671875, '3350270': 14.25390625, '3350272': 28.6953125, '3350274': 1073.6953125, '3350431': 28.4609375, '3350536': 31875.6875, '3350537': 46400.58203125, '3355767': 10248.6796875, '3355768': 10458.0625, '3359041': 28718.64453125, '3359040': 24276.71875, '3369327': 12273.33984375, '3369328': 12054.2109375, '3376054': 25775.203125, '3376055': 26078.109375} | {'3215898': 499.71, '3215933': 499.71, '3213061': 499.71, '3350270': 0.0, '3350272': 499.21, '3350274': 499.21, '3350431': 494.21, '3350536': 131.09, '3350537': 131.59, '3355767': 43.02, '3355768': 43.52, '3359041': 123.62, '3359040': 123.62, '3369327': 83.18, '3369328': 83.18, '3376054': 107.79, '3376055': 107.79} | {'3350536': 73580.0, '3350537': 706.0, '3355767': 73122.0, '3355768': 608.0, '3359040': 73646.0, '3359041': 896.0, '3369327': 73308.0, '3376054': 73668.0, '3376055': 608.0} | {'3350536': 98.04, '3350537': 59.53, '3355767': 36.52, '3355768': 24.01, '3359040': 109.62, '3359041': 71.6, '3369327': 68.53, '3376054': 96.28, '3376055': 61.3} | 2 | 3213061 | llmapi-models-2gpu | 5543.396 | 16148 | 500.0373916 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.098053207 | 1.338635002 | 1 | test_unittests[llmapi-models-2gpu] | 5 | 5 |
| 31 | test_unittests[model-gptneox] | NVIDIA H100 80GB HBM3 | 81559 | 9194 | 12978 | {'2384721': 126.98828125, '2394939': 10.32421875, '2394940': 21.9765625, '2470938': 29.37109375, '2470984': 12777.06640625, '2471144': 12.3671875} | {'2384721': 307.36, '2394939': 307.36, '2394940': 307.36, '2470938': 306.86, '2470984': 306.28, '2471144': 300.38} | {'2470984': 9194.0} | {'2470984': 278.29} | 1 | 2384721 | model-gptneox | 2149.491 | 16148 | 308.177759 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 8.870894061 | 7.574664817 | 7 | test_unittests[model-gptneox] | 0 | 6 |
| 32 | test_unittests[attention-bert] | NVIDIA H100 80GB HBM3 | 81559 | 2646 | 8230 | {'2384721': 126.984375, '2394939': 10.46484375, '2394940': 21.9921875, '2496903': 13.78125, '2496906': 28.46875, '2497122': 8031.26953125, '2497622': 12.4140625} | {'2384721': 404.75, '2394939': 404.75, '2394940': 404.75, '2496903': 0.0, '2496906': 404.25, '2497122': 403.75, '2497622': 399.74} | {'2497122': 2646.0} | {'2497122': 397.74} | 1 | 2384721 | attention-bert | 2149.491 | 16148 | 405.2302971 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 30.82350718 | 11.94459295 | 11 | test_unittests[attention-bert] | 0 | 49 |
| 33 | test_unittests[model_api-part2] | NVIDIA H100 80GB HBM3 | 81559 | 21854 | 27632 | {'2924976': 130.03515625, '2926291': 28.125, '2925940': 10.375, '2925941': 21.34375, '2926293': 27436.765625, '2926418': 13.28125} | {'2924976': 114.61, '2926291': 114.61, '2925940': 114.61, '2925941': 114.61, '2926293': 114.11, '2926418': 111.1} | {'2926293': 21854.0} | {'2926293': 109.6} | 1 | 2924976 | model_api-part2 | 2186.878 | 16148 | 115.4852654 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 3.731994143 | 3.55761436 | 3 | test_unittests[model_api-part2] | 0 | 1 |
| 34 | test_unittests[model-bert] | NVIDIA H100 80GB HBM3 | 81559 | 3114 | 8633 | {'2924976': 129.51953125, '2925940': 10.52734375, '2928532': 21.8125, '2925941': 21.3671875, '2928569': 28.24609375, '2928573': 8437.671875, '2928702': 11.44921875} | {'2924976': 201.19, '2925940': 201.19, '2928532': 0.0, '2925941': 201.19, '2928569': 200.69, '2928573': 200.19, '2928702': 196.68} | {'2928573': 3114.0} | {'2928573': 196.18} | 1 | 2924976 | model-bert | 2186.878 | 16148 | 201.6294354 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 26.19107258 | 11.38700336 | 11 | test_unittests[model-bert] | 0 | 21 |
| 35 | test_unittests[model-gpt-e2e] | NVIDIA H100 80GB HBM3 | 81559 | 3774 | 7779 | {'2924976': 129.1640625, '2945107': 23.984375, '2925940': 10.5234375, '2925941': 21.375, '2945110': 2610.09375, '2945108': 36.59375, '2945190': 11.44921875, '2945229': 1791.953125, '2945266': 10.5859375, '2945434': 7080.734375, '2945507': 10.59375, '2945691': 6402.07421875, '2945767': 10.62109375, '2946450': 988.015625, '2946526': 10.6015625, '2946583': 6392.0234375, '2946638': 10.59765625, '2946910': 6093.16796875, '2946946': 10.73046875, '2947678': 6201.0625, '2947717': 10.7265625, '2948445': 6334.33984375, '2948479': 10.58984375, '2949109': 5688.37890625, '2949187': 10.59375} | {'2924976': 202.69, '2945107': 0.0, '2925940': 202.69, '2925941': 202.69, '2945110': 202.19, '2945108': 202.19, '2945190': 199.19, '2945229': 5.0, '2945266': 2.5, '2945434': 19.02, '2945507': 16.01, '2945691': 28.03, '2945767': 25.02, '2946450': 4.0, '2946526': 1.0, '2946583': 20.52, '2946638': 17.01, '2946910': 29.03, '2946946': 26.53, '2947678': 29.53, '2947717': 26.52, '2948445': 24.02, '2948479': 21.02, '2949109': 24.02, '2949187': 21.02} | {'2945229': 990.0, '2945434': 1718.0, '2945691': 1786.0, '2946450': 1144.0, '2946583': 1720.0, '2946910': 1786.0, '2947678': 1812.0, '2948445': 1786.0, '2949109': 1812.0, '2945110': 3774.0} | {'2945229': 2.0, '2945434': 16.01, '2945691': 25.02, '2946450': 1.0, '2946583': 17.01, '2946910': 26.53, '2947678': 26.52, '2948445': 21.02, '2949109': 21.02, '2945110': 10.01} | 1 | 2924976 | model-gpt-e2e | 2186.878 | 16148 | 203.3154163 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 21.61075782 | 12.63709988 | 12 | test_unittests[model-gpt-e2e] | 0 | 1 |
| 36 | test_unittests[bindings] | NVIDIA H100 80GB HBM3 | 81559 | 73318 | 8780 | {'2924976': 130.4140625, '2925940': 10.58203125, '2925941': 21.375, '2949981': 12.73828125, '2949984': 29.296875, '2949986': 3059.69140625, '2950026': 11.41015625, '2950157': 387.73828125, '2950235': 10.5859375, '2950243': 2.91015625, '2950244': 0.3515625, '2950262': 0.375, '2950260': 4.80078125, '2950283': 9.87890625, '2950355': 0.8359375, '2950356': 0.1015625, '2950357': 0.4140625, '2950362': 1766.609375, '2950438': 10.58984375, '2950554': 7078.69921875, '2950591': 10.609375, '2950845': 6389.66796875, '2950882': 10.640625, '2951553': 967.55859375, '2951642': 10.7265625, '2951665': 6292.98046875, '2951702': 10.7265625, '2951947': 5585.6875, '2952005': 10.640625, '2952702': 6032.9296875, '2952738': 10.7265625, '2953406': 6379.98046875, '2953483': 10.78125, '2953773': 6231.16796875, '2953846': 10.66015625, '2954221': 6093.83203125, '2954260': 10.60546875, '2954569': 5934.36328125, '2954605': 10.7734375, '2956099': 6313.3828125, '2956228': 10.61328125, '2956484': 6106.0, '2956559': 10.58203125, '2956806': 5778.98828125, '2956874': 10.72265625, '2957279': 5916.52734375, '2957357': 10.609375, '2957782': 2231.20703125, '2957858': 10.796875, '2958211': 5627.8046875, '2958249': 10.63671875, '2959209': 5970.4375, '2959286': 10.796875, '2960405': 2141.9140625, '2960441': 10.75390625, '2960757': 185.78515625} | {'2924976': 369.66, '2925940': 369.66, '2925941': 369.66, '2949981': 0.0, '2949984': 369.16, '2949986': 368.66, '2950026': 365.66, '2950157': 290.77, '2950235': 288.26, '2950243': 0.5, '2950244': 0.0, '2950262': 0.0, '2950260': 0.0, '2950283': 0.0, '2950355': 2.0, '2950356': 2.0, '2950357': 2.0, '2950362': 4.5, '2950438': 1.5, '2950554': 19.52, '2950591': 16.01, '2950845': 27.52, '2950882': 25.02, '2951553': 4.5, '2951642': 1.5, '2951665': 20.02, '2951702': 17.52, '2951947': 29.03, '2952005': 26.52, '2952702': 23.52, '2952738': 21.02, '2953406': 10.51, '2953483': 8.01, '2953773': 10.51, '2953846': 7.51, '2954221': 10.51, '2954260': 7.51, '2954569': 22.02, '2954605': 19.52, '2956099': 10.51, '2956228': 8.01, '2956484': 10.51, '2956559': 7.51, '2956806': 10.51, '2956874': 8.01, '2957279': 10.51, '2957357': 8.01, '2957782': 21.52, '2957858': 19.02, '2958211': 13.51, '2958249': 11.01, '2959209': 13.51, '2959286': 11.01, '2960405': 14.01, '2960441': 11.01, '2960757': 0.5} | {'2949986': 73318.0, '2950362': 990.0, '2950554': 2198.0, '2950845': 1786.0, '2951553': 1070.0, '2951665': 1718.0, '2951947': 2024.0, '2952702': 1786.0, '2953406': 1810.0, '2953773': 1810.0, '2954221': 1812.0, '2954569': 1810.0, '2956099': 2048.0, '2956484': 1812.0, '2956806': 1810.0, '2957279': 2050.0, '2957782': 1618.0, '2958211': 2078.0, '2959209': 2078.0, '2960405': 4020.0} | {'2949986': 363.15, '2950362': 1.0, '2950554': 16.51, '2950845': 25.02, '2951553': 1.0, '2951665': 17.01, '2951947': 26.02, '2952702': 21.02, '2953406': 7.51, '2953773': 7.51, '2954221': 7.51, '2954569': 19.52, '2956099': 7.51, '2956484': 8.01, '2956806': 8.01, '2957279': 8.01, '2957782': 18.52, '2958211': 10.51, '2959209': 11.01, '2960405': 10.51} | 2 | 2924976 | bindings | 2186.878 | 16148 | 370.1046725 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.112400775 | 11.19635535 | 1 | test_unittests[bindings] | 18 | 49 |
| 37 | test_unittests[llmapi-quant] | NVIDIA H100 80GB HBM3 | 81559 | 73232 | 11930 | {'2924976': 130.06640625, '2972490': 17.015625, '2925940': 10.60546875, '2925941': 21.40625, '2972491': 28.375, '2972493': 11733.6328125, '2972533': 13.2734375, '2972941': 139.359375, '2972915': 1233.73828125, '2972889': 0.9765625, '2972890': 0.96484375, '2972891': 2.40234375, '2972925': 0.96484375, '2972960': 138.93359375, '2972944': 0.9609375, '2972963': 0.96484375, '2972979': 105.80078125, '2973017': 0.9609375, '2973033': 99.25, '2973034': 0.96484375, '2973050': 145.45703125, '2973069': 140.44140625, '2973053': 0.96484375, '2973122': 140.18359375, '2973106': 0.96484375, '2973124': 0.96484375, '2973140': 139.05859375, '2973159': 103.2890625, '2973143': 0.984375, '2973160': 0.9609375, '2973176': 152.046875, '2973193': 150.734375, '2973196': 17.78125, '2973177': 0.9609375, '2973197': 1947.59765625, '2973461': 2802.6484375, '2973609': 0.34765625, '2973625': 2804.48046875, '2973924': 2804.51171875, '2974098': 2803.97265625, '2974238': 27.71875, '2974254': 2803.203125, '2974486': 2803.21484375, '2974644': 2803.16015625, '2974909': 2803.0390625, '2975014': 26.63671875, '2975030': 2803.01953125, '2975256': 2803.57421875, '2975456': 1198.58203125, '2975440': 0.95703125} | {'2924976': 360.34, '2972490': 0.0, '2925940': 360.34, '2925941': 360.34, '2972491': 359.84, '2972493': 359.34, '2972533': 356.34, '2972941': 0.5, '2972915': 10.51, '2972889': 166.16, '2972890': 11.01, '2972891': 166.16, '2972925': 0.5, '2972960': 0.5, '2972944': 0.5, '2972963': 0.5, '2972979': 0.5, '2973017': 0.5, '2973033': 0.5, '2973034': 0.5, '2973050': 0.5, '2973069': 0.5, '2973053': 0.5, '2973122': 0.5, '2973106': 0.5, '2973124': 0.5, '2973140': 0.5, '2973159': 0.5, '2973143': 0.5, '2973160': 1.0, '2973176': 0.5, '2973193': 0.5, '2973196': 0.0, '2973177': 0.5, '2973197': 11.51, '2973461': 12.01, '2973609': 0.0, '2973625': 12.51, '2973924': 12.51, '2974098': 12.51, '2974238': 0.0, '2974254': 12.51, '2974486': 12.51, '2974644': 12.51, '2974909': 12.01, '2975014': 0.0, '2975030': 12.51, '2975256': 12.51, '2975456': 10.51, '2975440': 10.51} | {'2972493': 73232.0} | {'2972493': 354.84} | 1 | 2924976 | llmapi-quant | 2186.878 | 16148 | 360.6560194 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.113707123 | 8.240067058 | 1 | test_unittests[llmapi-quant] | 2 | 2 |
| 38 | test_unittests[attention-gpt-xqa-generic] | NVIDIA H100 80GB HBM3 | 81559 | 12842 | 11842 | {'222016': 25.25, '203762': 126.3671875, '206211': 10.40625, '206212': 22.01171875, '222019': 33.88671875, '222023': 11638.0390625, '222247': 11.70703125} | {'222016': 0.0, '203762': 6237.65, '206211': 6237.65, '206212': 6237.65, '222019': 6237.15, '222023': 6236.65, '222247': 6232.14} | {'222023': 12842.0} | {'222023': 6230.14} | 1 | 203762 | attention-gpt-xqa-generic | 7981.589 | 16148 | 6238.164207 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 6.350957795 | 8.301300456 | 6 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |
| 39 | test_unittests[functional-moe] | NVIDIA H100 80GB HBM3 | 81559 | 4788 | 9346 | {'203762': 127.22265625, '206211': 10.48828125, '206212': 22.0078125, '705621': 24.48046875, '705624': 28.72265625, '705626': 9146.296875, '705784': 11.6953125} | {'203762': 788.86, '206211': 788.86, '206212': 788.86, '705621': 0.0, '705624': 788.36, '705626': 787.86, '705784': 783.35} | {'705626': 4788.0} | {'705626': 781.85} | 1 | 203762 | functional-moe | 7981.589 | 16148 | 789.6104999 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 17.03404344 | 10.5182966 | 10 | test_unittests[functional-moe] | 0 | 82 |
| 40 | test_unittests[unit-woq-percol] | NVIDIA H100 80GB HBM3 | 81559 | 2208 | 7275 | {'203762': 127.1875, '206211': 10.49609375, '206212': 22.0078125, '940916': 28.22265625, '940919': 7075.88671875, '941171': 11.6953125} | {'203762': 141.11, '206211': 141.11, '206212': 141.11, '940916': 140.61, '940919': 140.11, '941171': 135.6} | {'940919': 2208.0} | {'940919': 133.6} | 1 | 203762 | unit-woq-percol | 7981.589 | 16148 | 141.2499655 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 36.9379529 | 13.51257732 | 13 | test_unittests[unit-woq-percol] | 0 | 18 |
| 41 | test_unittests[unit-woq-group] | NVIDIA H100 80GB HBM3 | 81559 | 1922 | 7544 | {'203762': 127.1875, '206211': 10.51171875, '206212': 22.0078125, '957533': 25.69921875, '957546': 28.4921875, '957550': 7345.2265625, '957751': 11.70703125} | {'203762': 288.27, '206211': 288.27, '206212': 288.27, '957533': 0.0, '957546': 287.77, '957550': 287.27, '957751': 283.27} | {'957550': 1922.0} | {'957550': 281.27} | 1 | 203762 | unit-woq-group | 7981.589 | 16148 | 288.8596221 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 42.43444329 | 13.03075292 | 13 | test_unittests[unit-woq-group] | 0 | 50 |
| 42 | test_unittests[attention-gpt-plugin-ib-mode] | NVIDIA H100 80GB HBM3 | 81559 | 2216 | 8471 | {'1865': 10.28125, '786': 130.33984375, '1866': 21.41796875, '2039': 19.18359375, '2040': 31.39453125, '2044': 8270.97265625, '2215': 13.2109375} | {'1865': 191.17, '786': 191.17, '1866': 191.17, '2039': 0.0, '2040': 190.67, '2044': 190.17, '2215': 187.17} | {'2044': 2216.0} | {'2044': 185.67} | 1 | 786 | attention-gpt-plugin-ib-mode | 1530.122 | 16148 | 191.7125493 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 36.80460289 | 11.60476921 | 11 | test_unittests[attention-gpt-plugin-ib-mode] | 0 | 34 |
| 43 | test_unittests[attention-gpt-no-cache] | NVIDIA H100 80GB HBM3 | 81559 | 1946 | 7393 | {'1865': 10.390625, '786': 131.29296875, '1866': 21.484375, '9534': 11.859375, '9584': 28.15625, '9587': 7196.453125, '9659': 13.1953125} | {'1865': 21.02, '786': 21.02, '1866': 21.02, '9534': 0.0, '9584': 20.52, '9587': 20.02, '9659': 17.02} | {'9587': 1946.0} | {'9587': 16.02} | 1 | 786 | attention-gpt-no-cache | 1530.122 | 16148 | 21.58346564 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 41.91109969 | 13.29690248 | 13 | test_unittests[attention-gpt-no-cache] | 0 | 2 |
| 44 | test_unittests[model-mamba] | NVIDIA H100 80GB HBM3 | 81559 | 2096 | 9791 | {'1865': 10.48046875, '786': 131.66796875, '19549': 45.97265625, '1866': 21.5078125, '19597': 12.453125, '19598': 28.2421875, '19602': 9593.8515625, '19642': 13.17578125} | {'1865': 321.3, '786': 321.3, '19549': 1.0, '1866': 321.3, '19597': 0.0, '19598': 319.3, '19602': 318.8, '19642': 315.8} | {'19602': 2096.0} | {'19602': 291.27} | 1 | 786 | model-mamba | 1530.122 | 16148 | 322.2435047 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 38.91173664 | 10.04024104 | 10 | test_unittests[model-mamba] | 0 | 12 |
| 45 | test_unittests[attention-gpt-partition0] | NVIDIA L40S | 46068 | 2622 | 6678 | {'3592777': 10.26953125, '3575269': 125.5703125, '3592791': 21.91796875, '3593032': 25.24609375, '3593046': 30.125, '3593140': 6480.46484375, '3593572': 11.703125} | {'3592777': 241.47, '3575269': 241.47, '3592791': 241.47, '3593032': 0.0, '3593046': 240.46, '3593140': 239.46, '3593572': 234.46} | {'3593140': 2622.0} | {'3593140': 231.88} | 1 | 3575269 | attention-gpt-partition0 | 4105.914 | 16148 | 241.3219729 | L40S-unittests | [L40S-unittests] Run TURTLE | 17.56979405 | 14.72057502 | 14 | test_unittests[attention-gpt-partition0] | 0 | 67 |
| 46 | test_unittests[attention-gpt-partition1] | NVIDIA L40S | 46068 | 4240 | 6669 | {'3592777': 10.41015625, '3575269': 124.58203125, '3592791': 21.91796875, '3629421': 6472.44921875, '3629404': 28.7109375, '3629626': 11.6953125} | {'3592777': 251.95, '3575269': 251.95, '3592791': 251.95, '3629421': 251.45, '3629404': 251.45, '3629626': 246.94} | {'3629421': 4240.0} | {'3629421': 244.44} | 1 | 3575269 | attention-gpt-partition1 | 4105.914 | 16148 | 252.5983796 | L40S-unittests | [L40S-unittests] Run TURTLE | 10.86509434 | 14.74044085 | 10 | test_unittests[attention-gpt-partition1] | 0 | 65 |
| 47 | test_unittests[attention-gpt-partition2] | NVIDIA L40S | 46068 | 7496 | 6726 | {'3592777': 10.4453125, '3651794': 25.24609375, '3575269': 124.5859375, '3592791': 21.9375, '3651821': 29.83984375, '3651842': 6529.80078125, '3652053': 11.69921875} | {'3592777': 222.64, '3651794': 0.0, '3575269': 222.64, '3592791': 222.64, '3651821': 222.14, '3651842': 221.14, '3652053': 217.14} | {'3651842': 7496.0} | {'3651842': 214.13} | 1 | 3575269 | attention-gpt-partition2 | 4105.914 | 16148 | 222.9654428 | L40S-unittests | [L40S-unittests] Run TURTLE | 6.145677695 | 14.61552186 | 6 | test_unittests[attention-gpt-partition2] | 0 | 66 |
| 48 | test_unittests[attention-gpt-partition3] | NVIDIA L40S | 46068 | 7492 | 6706 | {'3592777': 10.47265625, '3673329': 28.80859375, '3575269': 124.59375, '3592791': 21.9453125, '3673333': 6508.796875, '3673469': 11.69921875} | {'3592777': 229.63, '3673329': 229.63, '3575269': 229.63, '3592791': 229.63, '3673333': 229.13, '3673469': 224.13} | {'3673333': 7492.0} | {'3673333': 221.62} | 1 | 3575269 | attention-gpt-partition3 | 4105.914 | 16148 | 230.4534084 | L40S-unittests | [L40S-unittests] Run TURTLE | 6.148958889 | 14.65911124 | 6 | test_unittests[attention-gpt-partition3] | 0 | 65 |
| 49 | test_unittests[attention-gpt-xqa-generic] | NVIDIA L40S | 46068 | 12008 | 8760 | {'3592777': 10.50390625, '3575269': 124.59375, '3592791': 21.9375, '3691567': 18.91015625, '3691568': 33.0625, '3691570': 8558.125, '3691800': 12.484375} | {'3592777': 3018.28, '3575269': 3018.28, '3592791': 3018.28, '3691567': 0.0, '3691568': 3017.78, '3691570': 3017.28, '3691800': 3013.27} | {'3691570': 12008.0} | {'3691570': 3011.27} | 1 | 3575269 | attention-gpt-xqa-generic | 4105.914 | 16148 | 3018.694419 | L40S-unittests | [L40S-unittests] Run TURTLE | 3.836442372 | 11.22191781 | 3 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |
| 50 | test_unittests[functional] | NVIDIA L40S | 46068 | 12008 | 8760 | {'3592777': 10.50390625, '3575269': 124.59375, '3592791': 21.9375, '3691567': 18.91015625, '3691568': 33.0625, '3691570': 8558.125, '3691800': 12.484375} | {'3592777': 3018.28, '3575269': 3018.28, '3592791': 3018.28, '3691567': 0.0, '3691568': 3017.78, '3691570': 3017.28, '3691800': 3013.27} | {'3691570': 12008.0} | {'3691570': 3011.27} | 1 | 3575269 | functional | 4105.914 | 16148 | 3018.694419 | L40S-unittests | [L40S-unittests] Run TURTLE | 3.836442372 | 11.22191781 | 32 | test_unittests[functional] | 0 | 540 |
| 51 | test_unittests[attention-gpt-partition0] | Tesla PG500-216 | 32768 | 1246 | 3861 | {'637616': 10.26953125, '637629': 21.890625, '633327': 126.5078125, '637767': 23.69921875, '637772': 29.7890625, '637826': 3661.69921875, '638184': 11.6953125} | {'637616': 86.82, '637629': 86.82, '633327': 86.82, '637767': 0.0, '637772': 85.82, '637826': 84.82, '638184': 80.31} | {'637826': 1246.0} | {'637826': 76.81} | 1 | 633327 | attention-gpt-partition0 | 821.948 | 16148 | 86.88109152 | V100-unittests | [V100-unittests] Run TURTLE | 26.29855538 | 25.46076146 | 25 | test_unittests[attention-gpt-partition0] | 0 | 44 |
| 52 | test_unittests[attention-gpt-partition1] | Tesla PG500-216 | 32768 | 1248 | 3649 | {'637616': 10.4375, '650272': 18.43359375, '637629': 21.890625, '633327': 126.51171875, '650273': 28.77734375, '650290': 3450.77734375, '650898': 11.6953125} | {'637616': 80.62, '650272': 0.0, '637629': 80.62, '633327': 80.62, '650273': 80.12, '650290': 79.62, '650898': 75.61} | {'650290': 1248.0} | {'650290': 71.61} | 1 | 633327 | attention-gpt-partition1 | 821.948 | 16148 | 81.23641096 | V100-unittests | [V100-unittests] Run TURTLE | 26.25641026 | 26.93998356 | 26 | test_unittests[attention-gpt-partition1] | 0 | 44 |
| 53 | test_unittests[attention-gpt-partition2] | Tesla PG500-216 | 32768 | 6942 | 3508 | {'637616': 10.4453125, '637629': 21.890625, '633327': 126.51171875, '665944': 28.7578125, '665975': 3309.9453125, '666220': 11.6953125} | {'637616': 67.52, '637629': 67.52, '633327': 67.52, '665944': 67.02, '665975': 66.52, '666220': 62.01} | {'665975': 6942.0} | {'665975': 58.01} | 1 | 633327 | attention-gpt-partition2 | 821.948 | 16148 | 67.64402947 | V100-unittests | [V100-unittests] Run TURTLE | 4.720253529 | 28.02280502 | 4 | test_unittests[attention-gpt-partition2] | 0 | 44 |
| 54 | test_unittests[attention-gpt-partition3] | Tesla PG500-216 | 32768 | 6942 | 3436 | {'637616': 10.46875, '676844': 25.703125, '637629': 21.89453125, '633327': 126.51171875, '676850': 28.74609375, '676853': 3237.5390625, '677338': 11.6953125} | {'637616': 60.46, '676844': 0.0, '637629': 60.46, '633327': 60.46, '676850': 59.96, '676853': 59.96, '677338': 55.9} | {'676853': 6942.0} | {'676853': 51.9} | 1 | 633327 | attention-gpt-partition3 | 821.948 | 16148 | 61.20770215 | V100-unittests | [V100-unittests] Run TURTLE | 4.720253529 | 28.61001164 | 4 | test_unittests[attention-gpt-partition3] | 0 | 41 |
| 55 | test_unittests[attention-gpt-xqa-generic] | Tesla PG500-216 | 32768 | 10872 | 3731 | {'637616': 10.49609375, '685802': 18.62109375, '637629': 21.8984375, '633327': 126.51171875, '685892': 33.4296875, '685920': 3528.25, '686380': 11.6953125} | {'637616': 449.77, '685802': 0.0, '637629': 449.77, '633327': 449.77, '685892': 449.27, '685920': 448.77, '686380': 444.77} | {'685920': 10872.0} | {'685920': 391.72} | 1 | 633327 | attention-gpt-xqa-generic | 821.948 | 16148 | 450.2062255 | V100-unittests | [V100-unittests] Run TURTLE | 3.013980868 | 26.34789601 | 3 | test_unittests[attention-gpt-xqa-generic] | 0 | 219 |
| 56 | test_unittests[quantization] | Tesla PG500-216 | 32768 | 1114 | 2125 | {'2916740': 21.90625, '2916739': 10.265625, '2912228': 126.56640625, '2916953': 25.2421875, '2917051': 30.734375, '2917183': 1924.96484375, '2917566': 11.56640625} | {'2916740': 92.59, '2916739': 92.59, '2912228': 92.59, '2916953': 0.0, '2917051': 91.58, '2917183': 91.08, '2917566': 86.58} | {'2917183': 1114.0} | {'2917183': 83.58} | 1 | 2912228 | quantization | 1000.627 | 16148 | 92.54412255 | V100-functional-0 | [V100-functional-0] Run TURTLE | 29.41472172 | 46.26070588 | 29 | test_unittests[quantization] | 0 | 103 |
| 57 | test_unittests[model-gptj] | Tesla PG500-216 | 32768 | 4008 | 5245 | {'2916740': 21.91015625, '2916739': 10.3203125, '2912228': 126.5703125, '2925933': 25.70703125, '2926024': 5047.546875, '2925965': 28.171875, '2926429': 11.6953125} | {'2916740': 92.33, '2916739': 92.33, '2912228': 92.33, '2925933': 0.0, '2926024': 91.83, '2925965': 91.83, '2926429': 87.33} | {'2926024': 4008.0} | {'2926024': 76.82} | 1 | 2912228 | model-gptj | 1000.627 | 16148 | 93.15540791 | V100-functional-0 | [V100-functional-0] Run TURTLE | 8.175648703 | 18.74242135 | 8 | test_unittests[model-gptj] | 0 | 6 |
| 58 | test_unittests[functional] | Tesla PG500-216 | 32768 | 678 | 3039 | {'2916740': 21.921875, '2916739': 10.4375, '2912228': 126.57421875, '2994246': 34.296875, '2994251': 2834.90625, '2994493': 11.734375} | {'2916740': 454.94, '2916739': 454.94, '2912228': 454.94, '2994246': 453.94, '2994251': 453.94, '2994493': 449.43} | {'2994251': 678.0} | {'2994251': 447.43} | 1 | 2912228 | functional | 1000.627 | 16148 | 455.3922174 | V100-functional-0 | [V100-functional-0] Run TURTLE | 48.33038348 | 32.34748272 | 32 | test_unittests[functional] | 0 | 518 |
| 59 | test_unittests[others] | Tesla PG500-216 | 32768 | 30674 | 29889 | {'3186074': 124.99609375, '3192212': 10.3203125, '3192214': 21.953125, '3192411': 24.296875, '3192418': 40.6328125, '3192534': 29691.0, '3192778': 19.6796875, '3242492': 390.828125, '3242493': 390.51953125, '3242494': 390.453125, '3242495': 390.08203125, '3243153': 387.69921875, '3243154': 387.59765625, '3243123': 11.65234375, '3243155': 387.25, '3243156': 387.62109375} | {'3186074': 914.57, '3192212': 914.57, '3192214': 914.57, '3192411': 0.0, '3192418': 913.57, '3192534': 912.07, '3192778': 908.06, '3242492': 4.5, '3242493': 4.5, '3242494': 4.5, '3242495': 4.5, '3243153': 9.01, '3243154': 9.01, '3243123': 9.01, '3243155': 9.01, '3243156': 9.01} | {'3192534': 30674.0} | {'3192534': 905.56} | 1 | 3186074 | others | 1446.43 | 16148 | 914.456881 | V100-others-2 | [V100-others-2] Run TURTLE | 1.068266284 | 3.288969186 | 1 | test_unittests[others] | 2 | 580 |
| 60 | test_unittests[llmapi-models-part1] | Tesla PG500-216 | 32768 | 8138 | 18107 | {'3284464': 26.05078125, '3186074': 125.80859375, '3192212': 10.3828125, '3192214': 21.96875, '3284465': 28.46875, '3284467': 17909.3671875, '3284704': 12.42578125, '3290500': 62.51171875} | {'3284464': 0.0, '3186074': 295.13, '3192212': 295.13, '3192214': 295.13, '3284465': 294.63, '3284467': 294.63, '3284704': 289.62, '3290500': 4.5} | {'3284467': 8138.0} | {'3284467': 262.92} | 1 | 3186074 | llmapi-models-part1 | 1446.43 | 16148 | 295.7327851 | V100-others-2 | [V100-others-2] Run TURTLE | 4.026542148 | 5.429060584 | 4 | test_unittests[llmapi-models-part1] | 0 | 4 |
| 61 | test_unittests[llmapi-models-part3] | Tesla PG500-216 | 32768 | 12768 | 31442 | {'3186074': 125.859375, '3192214': 21.97265625, '3192212': 10.40625, '3294050': 24.140625, '3294051': 28.17578125, '3294054': 31245.20703125, '3294240': 11.625} | {'3186074': 168.97, '3192214': 168.97, '3192212': 168.97, '3294050': 0.0, '3294051': 168.47, '3294054': 167.97, '3294240': 163.46} | {'3294054': 12768.0} | {'3294054': 145.29} | 1 | 3186074 | llmapi-models-part3 | 1446.43 | 16148 | 169.4382996 | V100-others-2 | [V100-others-2] Run TURTLE | 2.56641604 | 3.126518669 | 2 | test_unittests[llmapi-models-part3] | 0 | 4 |
| 62 | test_unittests[model-gpt-partition0] | Tesla PG500-216 | 32768 | 990 | 2974 | {'635765': 10.26953125, '635909': 16.06640625, '631526': 122.97265625, '635766': 21.92578125, '636043': 29.87890625, '636062': 2778.65625, '636342': 11.69140625} | {'635765': 636.94, '635909': 0.0, '631526': 636.94, '635766': 636.94, '636043': 635.94, '636062': 634.93, '636342': 630.43} | {'636062': 990.0} | {'636062': 626.93} | 1 | 631526 | model-gpt-partition0 | 2733.493 | 16148 | 637.0551112 | V100-model-1 | [V100-model-1] Run TURTLE | 33.0989899 | 33.05447209 | 33 | test_unittests[model-gpt-partition0] | 0 | 75 |
| 63 | test_unittests[model-gpt-partition1] | Tesla PG500-216 | 32768 | 976 | 3449 | {'635766': 21.9375, '635765': 10.50390625, '631526': 122.1171875, '721293': 29.06640625, '721324': 3253.5234375, '721497': 14.28125} | {'635766': 602.72, '635765': 602.72, '631526': 602.72, '721293': 602.72, '721324': 602.22, '721497': 598.21} | {'721324': 976.0} | {'721324': 595.21} | 1 | 631526 | model-gpt-partition1 | 2733.493 | 16148 | 603.47751 | V100-model-1 | [V100-model-1] Run TURTLE | 33.57377049 | 28.50217454 | 28 | test_unittests[model-gpt-partition1] | 0 | 74 |
| 64 | test_unittests[model-gpt-partition2] | Tesla PG500-216 | 32768 | 1528 | 3540 | {'759769': 23.7734375, '635766': 22.09765625, '635765': 10.65625, '631526': 126.6640625, '759770': 29.71484375, '759772': 3345.10546875, '759924': 15.74609375} | {'759769': 0.0, '635766': 691.43, '635765': 691.43, '631526': 691.43, '759770': 690.93, '759772': 690.43, '759924': 686.43} | {'759772': 1528.0} | {'759772': 683.42} | 1 | 631526 | model-gpt-partition2 | 2733.493 | 16148 | 691.8112264 | V100-model-1 | [V100-model-1] Run TURTLE | 21.44502618 | 27.76949153 | 21 | test_unittests[model-gpt-partition2] | 0 | 76 |
| 65 | test_unittests[model-gpt-partition3] | Tesla PG500-216 | 32768 | 1522 | 3482 | {'780886': 25.703125, '635766': 21.98046875, '635765': 10.48046875, '631526': 125.53125, '780899': 28.8984375, '780901': 3287.78125, '781062': 12.421875} | {'780886': 0.0, '635766': 681.19, '635765': 681.19, '631526': 681.19, '780899': 680.69, '780901': 680.69, '781062': 675.69} | {'780901': 1522.0} | {'780901': 673.18} | 1 | 631526 | model-gpt-partition3 | 2733.493 | 16148 | 681.7204391 | V100-model-1 | [V100-model-1] Run TURTLE | 21.52956636 | 28.23205055 | 21 | test_unittests[model-gpt-partition3] | 0 | 74 |
| 66 | test_unittests[model-gpt-other] | Tesla PG500-216 | 32768 | 1542 | 3447 | {'811233': 25.2734375, '635766': 21.9296875, '635765': 10.515625, '631526': 121.99609375, '811319': 28.22265625, '811323': 3253.69140625, '811455': 11.6953125} | {'811233': 0.0, '635766': 62.13, '635765': 62.13, '631526': 62.13, '811319': 61.63, '811323': 61.13, '811455': 57.62} | {'811323': 1542.0} | {'811323': 53.62} | 1 | 631526 | model-gpt-other | 2733.493 | 16148 | 62.62592373 | V100-model-1 | [V100-model-1] Run TURTLE | 21.25032425 | 28.51871192 | 21 | test_unittests[model-gpt-other] | 0 | 4 |
| 67 | test_unittests[model-falcon] | Tesla PG500-216 | 32768 | 658 | 3051 | {'2925928': 10.26171875, '2925931': 21.875, '3000992': 16.82421875, '2911463': 136.48828125, '3001021': 29.5234375, '3001062': 2842.26953125, '3001428': 11.7109375} | {'2925928': 53.04, '2925931': 53.04, '3000992': 0.0, '2911463': 53.04, '3001021': 52.54, '3001062': 51.54, '3001428': 47.54} | {'3001062': 658.0} | {'3001062': 45.04} | 1 | 2911463 | model-falcon | 1425.894 | 16148 | 53.58859377 | V100-e2e_part1 | [V100-e2e_part1] Run TURTLE | 49.7993921 | 32.22025565 | 32 | test_unittests[model-falcon] | 0 | 12 |
| 68 | test_unittests[model-mistral] | Tesla PG500-216 | 32768 | 500 | 2936 | {'2925928': 10.4765625, '2925931': 21.9296875, '3043653': 25.33984375, '2911463': 140.8359375, '3043736': 28.63671875, '3043738': 2727.4609375, '3043838': 14.20703125} | {'2925928': 71.06, '2925931': 71.06, '3043653': 0.0, '2911463': 71.06, '3043736': 70.56, '3043738': 70.06, '3043838': 66.06} | {'3043738': 500.0} | {'3043738': 62.55} | 1 | 2911463 | model-mistral | 1425.894 | 16148 | 71.5794183 | V100-e2e_part1 | [V100-e2e_part1] Run TURTLE | 65.536 | 33.48228883 | 33 | test_unittests[model-mistral] | 0 | 22 |
| 69 | test_unittests[model-bert] | Tesla PG500-216 | 32768 | 1538 | 3503 | {'641192': 23.7109375, '634259': 126.55078125, '638428': 21.90234375, '638427': 10.4453125, '641261': 28.23046875, '641285': 3304.54296875, '641540': 11.6953125} | {'641192': 0.0, '634259': 193.08, '638428': 193.08, '638427': 193.08, '641261': 192.58, '641285': 192.08, '641540': 188.08} | {'641285': 1538.0} | {'641285': 186.07} | 1 | 634259 | model-bert | 894.343 | 16148 | 193.707374 | V100-others-0 | [V100-others-0] Run TURTLE | 21.30559168 | 28.06280331 | 21 | test_unittests[model-bert] | 0 | 17 |
| 70 | test_unittests[model-gpt-e2e] | Tesla PG500-216 | 32768 | 2922 | 3432 | {'676520': 12.07421875, '634259': 126.5546875, '638428': 21.91015625, '638427': 10.4609375, '676521': 33.921875, '676523': 2012.21484375, '676851': 11.69921875, '677072': 1795.19921875, '677534': 11.5546875, '679627': 2761.18359375, '680146': 11.6953125, '682704': 2284.83984375, '683074': 11.69921875, '686311': 1188.79296875, '686492': 11.6953125, '686838': 2064.29296875, '686962': 11.6953125, '688501': 1742.80859375, '689377': 11.69921875, '692508': 1731.8359375, '693201': 11.69921875} | {'676520': 0.0, '634259': 179.78, '638428': 179.78, '638427': 179.78, '676521': 179.28, '676523': 178.78, '676851': 174.78, '677072': 11.84, '677534': 7.84, '679627': 19.02, '680146': 15.51, '682704': 30.53, '683074': 27.02, '686311': 10.8, '686492': 6.8, '686838': 21.52, '686962': 18.02, '688501': 33.53, '689377': 30.03, '692508': 27.02, '693201': 23.52} | {'677072': 822.0, '679627': 360.0, '682704': 848.0, '686311': 948.0, '686838': 360.0, '688501': 610.0, '692508': 372.0, '676523': 2922.0} | {'677072': 4.95, '679627': 15.01, '682704': 26.52, '686311': 4.29, '686838': 17.52, '688501': 29.53, '692508': 22.52, '676523': 14.51} | 1 | 634259 | model-gpt-e2e | 894.343 | 16148 | 180.0751595 | V100-others-0 | [V100-others-0] Run TURTLE | 11.21423682 | 28.64335664 | 11 | test_unittests[model-gpt-e2e] | 0 | 1 |
| 71 | test_unittests[bindings] | Tesla PG500-216 | 32768 | 280 | 1362 | {'697211': 25.28125, '634259': 126.5546875, '638428': 21.91015625, '638427': 10.4765625, '697227': 28.6015625, '697262': 1163.82421875, '697627': 11.7109375} | {'697211': 0.0, '634259': 25.52, '638428': 25.52, '638427': 25.52, '697227': 25.02, '697262': 24.52, '697627': 20.02} | {'697262': 280.0} | {'697262': 16.01} | 1 | 634259 | bindings | 894.343 | 16148 | 26.16358308 | V100-others-0 | [V100-others-0] Run TURTLE | 117.0285714 | 72.17621145 | 72 | test_unittests[bindings] | 0 | 31 |
| 72 | test_unittests[model-falcon] | Tesla PG500-216 | 32768 | 674 | 3113 | {'736881': 10.2734375, '736882': 21.89453125, '730453': 133.03515625, '786022': 29.5390625, '786090': 2918.87109375} | {'736881': 55.17, '736882': 55.17, '730453': 55.17, '786022': 54.67, '786090': 53.67} | {'786090': 674.0} | {'786090': 47.66} | 1 | 730453 | model-falcon | 1183.509 | 16148 | 55.6215516 | V100-Single-e2e-part1 | [V100-Single-e2e-part1] Run TURTLE | 48.61721068 | 31.5785416 | 31 | test_unittests[model-falcon] | 0 | 12 |
| 73 | test_unittests[model-mistral] | Tesla PG500-216 | 32768 | 508 | 2920 | {'736881': 10.62890625, '736882': 21.99609375, '730453': 138.90234375, '811585': 29.29296875, '811627': 2726.79296875} | {'736881': 70.56, '736882': 70.56, '730453': 70.56, '811585': 70.06, '811627': 69.56} | {'811627': 508.0} | {'811627': 61.05} | 1 | 730453 | model-mistral | 1183.509 | 16148 | 70.64076682 | V100-Single-e2e-part1 | [V100-Single-e2e-part1] Run TURTLE | 64.50393701 | 33.66575342 | 33 | test_unittests[model-mistral] | 0 | 20 |
| 74 | test_unittests[llmapi-tp-2gpu] | NVIDIA H100 PCIe | 81559 | 73756 | 27628 | {'3215898': 10.3359375, '3215933': 21.49609375, '3213061': 130.5, '3323042': 30.0546875, '3323055': 12172.48828125, '3323325': 29.2265625, '3323842': 8266.75390625, '3323843': 8935.0859375, '3326674': 2611.1953125, '3326675': 2611.8046875, '3326906': 2605.125, '3326905': 2607.7578125, '3327221': 2596.72265625, '3327222': 2596.32421875, '3329303': 8834.60546875, '3329304': 8454.85546875, '3332276': 8050.3359375, '3332277': 9001.72265625, '3334107': 8570.27734375, '3334108': 8940.27734375, '3337392': 8802.87109375, '3337393': 9091.703125, '3340439': 8662.23046875, '3340440': 8963.91796875, '3343414': 8724.72265625, '3343415': 8828.78515625, '3346319': 11.6875, '3346336': 0.3828125, '3346337': 0.37890625, '3346360': 2604.953125, '3346366': 2609.21875, '3346776': 8781.49609375, '3346780': 8883.0} | {'3215898': 420.74, '3215933': 420.74, '3213061': 420.74, '3323042': 420.24, '3323055': 419.74, '3323325': 414.73, '3323842': 40.53, '3323843': 41.53, '3326674': 7.51, '3326675': 7.51, '3326906': 9.51, '3326905': 9.51, '3327221': 7.51, '3327222': 7.51, '3329303': 43.02, '3329304': 43.02, '3332276': 49.03, '3332277': 49.03, '3334107': 45.52, '3334108': 46.02, '3337392': 36.52, '3337393': 37.02, '3340439': 45.52, '3340440': 46.52, '3343414': 37.02, '3343415': 37.52, '3346319': 12.01, '3346336': 11.51, '3346337': 11.51, '3346360': 11.51, '3346366': 11.51, '3346776': 45.02, '3346780': 45.02} | {'3323842': 3074.0, '3323843': 610.0, '3326674': 73454.0, '3326905': 34118.0, '3327221': 34118.0, '3323055': 4062.0, '3329303': 34332.0, '3329304': 896.0, '3332276': 33510.0, '3332277': 608.0, '3334107': 72426.0, '3334108': 896.0, '3337392': 72432.0, '3337393': 896.0, '3340439': 72422.0, '3340440': 896.0, '3343414': 72492.0, '3343415': 608.0, '3346360': 72858.0, '3346776': 34398.0, '3346780': 610.0} | {'3323842': 35.52, '3323843': 23.01, '3326674': 3.5, '3326905': 4.5, '3327221': 4.0, '3323055': 347.68, '3329303': 38.02, '3329304': 24.01, '3332276': 44.52, '3332277': 35.52, '3334107': 40.02, '3334108': 26.01, '3337392': 32.01, '3337393': 21.01, '3340439': 40.02, '3340440': 26.01, '3343414': 32.51, '3343415': 21.01, '3346360': 4.0, '3346776': 40.52, '3346780': 27.51} | 3 | 3213061 | llmapi-tp-2gpu | 5543.396 | 16148 | 421.1721736 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.105794783 | 3.558129434 | 1 | test_unittests[llmapi-tp-2gpu] | 6 | 13 |
| 75 | test_unittests[llmapi-models-2gpu] | NVIDIA H100 PCIe | 81559 | 74276 | 73436 | {'3215898': 10.44140625, '3215933': 21.50390625, '3213061': 127.8671875, '3350270': 14.25390625, '3350272': 28.6953125, '3350274': 1073.6953125, '3350431': 28.4609375, '3350536': 31875.6875, '3350537': 46400.58203125, '3355767': 10248.6796875, '3355768': 10458.0625, '3359041': 28718.64453125, '3359040': 24276.71875, '3369327': 12273.33984375, '3369328': 12054.2109375, '3376054': 25775.203125, '3376055': 26078.109375} | {'3215898': 499.71, '3215933': 499.71, '3213061': 499.71, '3350270': 0.0, '3350272': 499.21, '3350274': 499.21, '3350431': 494.21, '3350536': 131.09, '3350537': 131.59, '3355767': 43.02, '3355768': 43.52, '3359041': 123.62, '3359040': 123.62, '3369327': 83.18, '3369328': 83.18, '3376054': 107.79, '3376055': 107.79} | {'3350536': 73580.0, '3350537': 706.0, '3355767': 73122.0, '3355768': 608.0, '3359040': 73646.0, '3359041': 896.0, '3369327': 73308.0, '3376054': 73668.0, '3376055': 608.0} | {'3350536': 98.04, '3350537': 59.53, '3355767': 36.52, '3355768': 24.01, '3359040': 109.62, '3359041': 71.6, '3369327': 68.53, '3376054': 96.28, '3376055': 61.3} | 2 | 3213061 | llmapi-models-2gpu | 5543.396 | 16148 | 500.0373916 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.098053207 | 1.338635002 | 1 | test_unittests[llmapi-models-2gpu] | 5 | 5 |
| 76 | test_unittests[model-gptneox] | NVIDIA H100 PCIe | 81559 | 9194 | 12978 | {'2384721': 126.98828125, '2394939': 10.32421875, '2394940': 21.9765625, '2470938': 29.37109375, '2470984': 12777.06640625, '2471144': 12.3671875} | {'2384721': 307.36, '2394939': 307.36, '2394940': 307.36, '2470938': 306.86, '2470984': 306.28, '2471144': 300.38} | {'2470984': 9194.0} | {'2470984': 278.29} | 1 | 2384721 | model-gptneox | 2149.491 | 16148 | 308.177759 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 8.870894061 | 7.574664817 | 7 | test_unittests[model-gptneox] | 0 | 6 |
| 77 | test_unittests[attention-bert] | NVIDIA H100 PCIe | 81559 | 2646 | 8230 | {'2384721': 126.984375, '2394939': 10.46484375, '2394940': 21.9921875, '2496903': 13.78125, '2496906': 28.46875, '2497122': 8031.26953125, '2497622': 12.4140625} | {'2384721': 404.75, '2394939': 404.75, '2394940': 404.75, '2496903': 0.0, '2496906': 404.25, '2497122': 403.75, '2497622': 399.74} | {'2497122': 2646.0} | {'2497122': 397.74} | 1 | 2384721 | attention-bert | 2149.491 | 16148 | 405.2302971 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 30.82350718 | 11.94459295 | 11 | test_unittests[attention-bert] | 0 | 49 |
| 78 | test_unittests[model_api-part2] | NVIDIA H100 PCIe | 81559 | 21854 | 27632 | {'2924976': 130.03515625, '2926291': 28.125, '2925940': 10.375, '2925941': 21.34375, '2926293': 27436.765625, '2926418': 13.28125} | {'2924976': 114.61, '2926291': 114.61, '2925940': 114.61, '2925941': 114.61, '2926293': 114.11, '2926418': 111.1} | {'2926293': 21854.0} | {'2926293': 109.6} | 1 | 2924976 | model_api-part2 | 2186.878 | 16148 | 115.4852654 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 3.731994143 | 3.55761436 | 3 | test_unittests[model_api-part2] | 0 | 1 |
| 79 | test_unittests[model-bert] | NVIDIA H100 PCIe | 81559 | 3114 | 8633 | {'2924976': 129.51953125, '2925940': 10.52734375, '2928532': 21.8125, '2925941': 21.3671875, '2928569': 28.24609375, '2928573': 8437.671875, '2928702': 11.44921875} | {'2924976': 201.19, '2925940': 201.19, '2928532': 0.0, '2925941': 201.19, '2928569': 200.69, '2928573': 200.19, '2928702': 196.68} | {'2928573': 3114.0} | {'2928573': 196.18} | 1 | 2924976 | model-bert | 2186.878 | 16148 | 201.6294354 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 26.19107258 | 11.38700336 | 11 | test_unittests[model-bert] | 0 | 21 |
| 80 | test_unittests[model-gpt-e2e] | NVIDIA H100 PCIe | 81559 | 3774 | 7779 | {'2924976': 129.1640625, '2945107': 23.984375, '2925940': 10.5234375, '2925941': 21.375, '2945110': 2610.09375, '2945108': 36.59375, '2945190': 11.44921875, '2945229': 1791.953125, '2945266': 10.5859375, '2945434': 7080.734375, '2945507': 10.59375, '2945691': 6402.07421875, '2945767': 10.62109375, '2946450': 988.015625, '2946526': 10.6015625, '2946583': 6392.0234375, '2946638': 10.59765625, '2946910': 6093.16796875, '2946946': 10.73046875, '2947678': 6201.0625, '2947717': 10.7265625, '2948445': 6334.33984375, '2948479': 10.58984375, '2949109': 5688.37890625, '2949187': 10.59375} | {'2924976': 202.69, '2945107': 0.0, '2925940': 202.69, '2925941': 202.69, '2945110': 202.19, '2945108': 202.19, '2945190': 199.19, '2945229': 5.0, '2945266': 2.5, '2945434': 19.02, '2945507': 16.01, '2945691': 28.03, '2945767': 25.02, '2946450': 4.0, '2946526': 1.0, '2946583': 20.52, '2946638': 17.01, '2946910': 29.03, '2946946': 26.53, '2947678': 29.53, '2947717': 26.52, '2948445': 24.02, '2948479': 21.02, '2949109': 24.02, '2949187': 21.02} | {'2945229': 990.0, '2945434': 1718.0, '2945691': 1786.0, '2946450': 1144.0, '2946583': 1720.0, '2946910': 1786.0, '2947678': 1812.0, '2948445': 1786.0, '2949109': 1812.0, '2945110': 3774.0} | {'2945229': 2.0, '2945434': 16.01, '2945691': 25.02, '2946450': 1.0, '2946583': 17.01, '2946910': 26.53, '2947678': 26.52, '2948445': 21.02, '2949109': 21.02, '2945110': 10.01} | 1 | 2924976 | model-gpt-e2e | 2186.878 | 16148 | 203.3154163 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 21.61075782 | 12.63709988 | 12 | test_unittests[model-gpt-e2e] | 0 | 1 |
| 81 | test_unittests[bindings] | NVIDIA H100 PCIe | 81559 | 73318 | 8780 | {'2924976': 130.4140625, '2925940': 10.58203125, '2925941': 21.375, '2949981': 12.73828125, '2949984': 29.296875, '2949986': 3059.69140625, '2950026': 11.41015625, '2950157': 387.73828125, '2950235': 10.5859375, '2950243': 2.91015625, '2950244': 0.3515625, '2950262': 0.375, '2950260': 4.80078125, '2950283': 9.87890625, '2950355': 0.8359375, '2950356': 0.1015625, '2950357': 0.4140625, '2950362': 1766.609375, '2950438': 10.58984375, '2950554': 7078.69921875, '2950591': 10.609375, '2950845': 6389.66796875, '2950882': 10.640625, '2951553': 967.55859375, '2951642': 10.7265625, '2951665': 6292.98046875, '2951702': 10.7265625, '2951947': 5585.6875, '2952005': 10.640625, '2952702': 6032.9296875, '2952738': 10.7265625, '2953406': 6379.98046875, '2953483': 10.78125, '2953773': 6231.16796875, '2953846': 10.66015625, '2954221': 6093.83203125, '2954260': 10.60546875, '2954569': 5934.36328125, '2954605': 10.7734375, '2956099': 6313.3828125, '2956228': 10.61328125, '2956484': 6106.0, '2956559': 10.58203125, '2956806': 5778.98828125, '2956874': 10.72265625, '2957279': 5916.52734375, '2957357': 10.609375, '2957782': 2231.20703125, '2957858': 10.796875, '2958211': 5627.8046875, '2958249': 10.63671875, '2959209': 5970.4375, '2959286': 10.796875, '2960405': 2141.9140625, '2960441': 10.75390625, '2960757': 185.78515625} | {'2924976': 369.66, '2925940': 369.66, '2925941': 369.66, '2949981': 0.0, '2949984': 369.16, '2949986': 368.66, '2950026': 365.66, '2950157': 290.77, '2950235': 288.26, '2950243': 0.5, '2950244': 0.0, '2950262': 0.0, '2950260': 0.0, '2950283': 0.0, '2950355': 2.0, '2950356': 2.0, '2950357': 2.0, '2950362': 4.5, '2950438': 1.5, '2950554': 19.52, '2950591': 16.01, '2950845': 27.52, '2950882': 25.02, '2951553': 4.5, '2951642': 1.5, '2951665': 20.02, '2951702': 17.52, '2951947': 29.03, '2952005': 26.52, '2952702': 23.52, '2952738': 21.02, '2953406': 10.51, '2953483': 8.01, '2953773': 10.51, '2953846': 7.51, '2954221': 10.51, '2954260': 7.51, '2954569': 22.02, '2954605': 19.52, '2956099': 10.51, '2956228': 8.01, '2956484': 10.51, '2956559': 7.51, '2956806': 10.51, '2956874': 8.01, '2957279': 10.51, '2957357': 8.01, '2957782': 21.52, '2957858': 19.02, '2958211': 13.51, '2958249': 11.01, '2959209': 13.51, '2959286': 11.01, '2960405': 14.01, '2960441': 11.01, '2960757': 0.5} | {'2949986': 73318.0, '2950362': 990.0, '2950554': 2198.0, '2950845': 1786.0, '2951553': 1070.0, '2951665': 1718.0, '2951947': 2024.0, '2952702': 1786.0, '2953406': 1810.0, '2953773': 1810.0, '2954221': 1812.0, '2954569': 1810.0, '2956099': 2048.0, '2956484': 1812.0, '2956806': 1810.0, '2957279': 2050.0, '2957782': 1618.0, '2958211': 2078.0, '2959209': 2078.0, '2960405': 4020.0} | {'2949986': 363.15, '2950362': 1.0, '2950554': 16.51, '2950845': 25.02, '2951553': 1.0, '2951665': 17.01, '2951947': 26.02, '2952702': 21.02, '2953406': 7.51, '2953773': 7.51, '2954221': 7.51, '2954569': 19.52, '2956099': 7.51, '2956484': 8.01, '2956806': 8.01, '2957279': 8.01, '2957782': 18.52, '2958211': 10.51, '2959209': 11.01, '2960405': 10.51} | 2 | 2924976 | bindings | 2186.878 | 16148 | 370.1046725 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.112400775 | 11.19635535 | 1 | test_unittests[bindings] | 18 | 49 |
| 82 | test_unittests[llmapi-quant] | NVIDIA H100 PCIe | 81559 | 73232 | 11930 | {'2924976': 130.06640625, '2972490': 17.015625, '2925940': 10.60546875, '2925941': 21.40625, '2972491': 28.375, '2972493': 11733.6328125, '2972533': 13.2734375, '2972941': 139.359375, '2972915': 1233.73828125, '2972889': 0.9765625, '2972890': 0.96484375, '2972891': 2.40234375, '2972925': 0.96484375, '2972960': 138.93359375, '2972944': 0.9609375, '2972963': 0.96484375, '2972979': 105.80078125, '2973017': 0.9609375, '2973033': 99.25, '2973034': 0.96484375, '2973050': 145.45703125, '2973069': 140.44140625, '2973053': 0.96484375, '2973122': 140.18359375, '2973106': 0.96484375, '2973124': 0.96484375, '2973140': 139.05859375, '2973159': 103.2890625, '2973143': 0.984375, '2973160': 0.9609375, '2973176': 152.046875, '2973193': 150.734375, '2973196': 17.78125, '2973177': 0.9609375, '2973197': 1947.59765625, '2973461': 2802.6484375, '2973609': 0.34765625, '2973625': 2804.48046875, '2973924': 2804.51171875, '2974098': 2803.97265625, '2974238': 27.71875, '2974254': 2803.203125, '2974486': 2803.21484375, '2974644': 2803.16015625, '2974909': 2803.0390625, '2975014': 26.63671875, '2975030': 2803.01953125, '2975256': 2803.57421875, '2975456': 1198.58203125, '2975440': 0.95703125} | {'2924976': 360.34, '2972490': 0.0, '2925940': 360.34, '2925941': 360.34, '2972491': 359.84, '2972493': 359.34, '2972533': 356.34, '2972941': 0.5, '2972915': 10.51, '2972889': 166.16, '2972890': 11.01, '2972891': 166.16, '2972925': 0.5, '2972960': 0.5, '2972944': 0.5, '2972963': 0.5, '2972979': 0.5, '2973017': 0.5, '2973033': 0.5, '2973034': 0.5, '2973050': 0.5, '2973069': 0.5, '2973053': 0.5, '2973122': 0.5, '2973106': 0.5, '2973124': 0.5, '2973140': 0.5, '2973159': 0.5, '2973143': 0.5, '2973160': 1.0, '2973176': 0.5, '2973193': 0.5, '2973196': 0.0, '2973177': 0.5, '2973197': 11.51, '2973461': 12.01, '2973609': 0.0, '2973625': 12.51, '2973924': 12.51, '2974098': 12.51, '2974238': 0.0, '2974254': 12.51, '2974486': 12.51, '2974644': 12.51, '2974909': 12.01, '2975014': 0.0, '2975030': 12.51, '2975256': 12.51, '2975456': 10.51, '2975440': 10.51} | {'2972493': 73232.0} | {'2972493': 354.84} | 1 | 2924976 | llmapi-quant | 2186.878 | 16148 | 360.6560194 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.113707123 | 8.240067058 | 1 | test_unittests[llmapi-quant] | 2 | 2 |
| 83 | test_unittests[attention-gpt-xqa-generic] | NVIDIA H100 PCIe | 81559 | 12842 | 11842 | {'222016': 25.25, '203762': 126.3671875, '206211': 10.40625, '206212': 22.01171875, '222019': 33.88671875, '222023': 11638.0390625, '222247': 11.70703125} | {'222016': 0.0, '203762': 6237.65, '206211': 6237.65, '206212': 6237.65, '222019': 6237.15, '222023': 6236.65, '222247': 6232.14} | {'222023': 12842.0} | {'222023': 6230.14} | 1 | 203762 | attention-gpt-xqa-generic | 7981.589 | 16148 | 6238.164207 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 6.350957795 | 8.301300456 | 6 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |
| 84 | test_unittests[functional-moe] | NVIDIA H100 PCIe | 81559 | 4788 | 9346 | {'203762': 127.22265625, '206211': 10.48828125, '206212': 22.0078125, '705621': 24.48046875, '705624': 28.72265625, '705626': 9146.296875, '705784': 11.6953125} | {'203762': 788.86, '206211': 788.86, '206212': 788.86, '705621': 0.0, '705624': 788.36, '705626': 787.86, '705784': 783.35} | {'705626': 4788.0} | {'705626': 781.85} | 1 | 203762 | functional-moe | 7981.589 | 16148 | 789.6104999 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 17.03404344 | 10.5182966 | 10 | test_unittests[functional-moe] | 0 | 82 |
| 85 | test_unittests[unit-woq-percol] | NVIDIA H100 PCIe | 81559 | 2208 | 7275 | {'203762': 127.1875, '206211': 10.49609375, '206212': 22.0078125, '940916': 28.22265625, '940919': 7075.88671875, '941171': 11.6953125} | {'203762': 141.11, '206211': 141.11, '206212': 141.11, '940916': 140.61, '940919': 140.11, '941171': 135.6} | {'940919': 2208.0} | {'940919': 133.6} | 1 | 203762 | unit-woq-percol | 7981.589 | 16148 | 141.2499655 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 36.9379529 | 13.51257732 | 13 | test_unittests[unit-woq-percol] | 0 | 18 |
| 86 | test_unittests[unit-woq-group] | NVIDIA H100 PCIe | 81559 | 1922 | 7544 | {'203762': 127.1875, '206211': 10.51171875, '206212': 22.0078125, '957533': 25.69921875, '957546': 28.4921875, '957550': 7345.2265625, '957751': 11.70703125} | {'203762': 288.27, '206211': 288.27, '206212': 288.27, '957533': 0.0, '957546': 287.77, '957550': 287.27, '957751': 283.27} | {'957550': 1922.0} | {'957550': 281.27} | 1 | 203762 | unit-woq-group | 7981.589 | 16148 | 288.8596221 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 42.43444329 | 13.03075292 | 13 | test_unittests[unit-woq-group] | 0 | 50 |
| 87 | test_unittests[attention-gpt-plugin-ib-mode] | NVIDIA H100 PCIe | 81559 | 2216 | 8471 | {'1865': 10.28125, '786': 130.33984375, '1866': 21.41796875, '2039': 19.18359375, '2040': 31.39453125, '2044': 8270.97265625, '2215': 13.2109375} | {'1865': 191.17, '786': 191.17, '1866': 191.17, '2039': 0.0, '2040': 190.67, '2044': 190.17, '2215': 187.17} | {'2044': 2216.0} | {'2044': 185.67} | 1 | 786 | attention-gpt-plugin-ib-mode | 1530.122 | 16148 | 191.7125493 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 36.80460289 | 11.60476921 | 11 | test_unittests[attention-gpt-plugin-ib-mode] | 0 | 34 |
| 88 | test_unittests[attention-gpt-no-cache] | NVIDIA H100 PCIe | 81559 | 1946 | 7393 | {'1865': 10.390625, '786': 131.29296875, '1866': 21.484375, '9534': 11.859375, '9584': 28.15625, '9587': 7196.453125, '9659': 13.1953125} | {'1865': 21.02, '786': 21.02, '1866': 21.02, '9534': 0.0, '9584': 20.52, '9587': 20.02, '9659': 17.02} | {'9587': 1946.0} | {'9587': 16.02} | 1 | 786 | attention-gpt-no-cache | 1530.122 | 16148 | 21.58346564 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 41.91109969 | 13.29690248 | 13 | test_unittests[attention-gpt-no-cache] | 0 | 2 |
| 89 | test_unittests[model-mamba] | NVIDIA H100 PCIe | 81559 | 2096 | 9791 | {'1865': 10.48046875, '786': 131.66796875, '19549': 45.97265625, '1866': 21.5078125, '19597': 12.453125, '19598': 28.2421875, '19602': 9593.8515625, '19642': 13.17578125} | {'1865': 321.3, '786': 321.3, '19549': 1.0, '1866': 321.3, '19597': 0.0, '19598': 319.3, '19602': 318.8, '19642': 315.8} | {'19602': 2096.0} | {'19602': 291.27} | 1 | 786 | model-mamba | 1530.122 | 16148 | 322.2435047 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 38.91173664 | 10.04024104 | 10 | test_unittests[model-mamba] | 0 | 12 |
| 90 | test_unittests[llmapi-tp-2gpu] | NVIDIA H100 NVL | 81559 | 73756 | 27628 | {'3215898': 10.3359375, '3215933': 21.49609375, '3213061': 130.5, '3323042': 30.0546875, '3323055': 12172.48828125, '3323325': 29.2265625, '3323842': 8266.75390625, '3323843': 8935.0859375, '3326674': 2611.1953125, '3326675': 2611.8046875, '3326906': 2605.125, '3326905': 2607.7578125, '3327221': 2596.72265625, '3327222': 2596.32421875, '3329303': 8834.60546875, '3329304': 8454.85546875, '3332276': 8050.3359375, '3332277': 9001.72265625, '3334107': 8570.27734375, '3334108': 8940.27734375, '3337392': 8802.87109375, '3337393': 9091.703125, '3340439': 8662.23046875, '3340440': 8963.91796875, '3343414': 8724.72265625, '3343415': 8828.78515625, '3346319': 11.6875, '3346336': 0.3828125, '3346337': 0.37890625, '3346360': 2604.953125, '3346366': 2609.21875, '3346776': 8781.49609375, '3346780': 8883.0} | {'3215898': 420.74, '3215933': 420.74, '3213061': 420.74, '3323042': 420.24, '3323055': 419.74, '3323325': 414.73, '3323842': 40.53, '3323843': 41.53, '3326674': 7.51, '3326675': 7.51, '3326906': 9.51, '3326905': 9.51, '3327221': 7.51, '3327222': 7.51, '3329303': 43.02, '3329304': 43.02, '3332276': 49.03, '3332277': 49.03, '3334107': 45.52, '3334108': 46.02, '3337392': 36.52, '3337393': 37.02, '3340439': 45.52, '3340440': 46.52, '3343414': 37.02, '3343415': 37.52, '3346319': 12.01, '3346336': 11.51, '3346337': 11.51, '3346360': 11.51, '3346366': 11.51, '3346776': 45.02, '3346780': 45.02} | {'3323842': 3074.0, '3323843': 610.0, '3326674': 73454.0, '3326905': 34118.0, '3327221': 34118.0, '3323055': 4062.0, '3329303': 34332.0, '3329304': 896.0, '3332276': 33510.0, '3332277': 608.0, '3334107': 72426.0, '3334108': 896.0, '3337392': 72432.0, '3337393': 896.0, '3340439': 72422.0, '3340440': 896.0, '3343414': 72492.0, '3343415': 608.0, '3346360': 72858.0, '3346776': 34398.0, '3346780': 610.0} | {'3323842': 35.52, '3323843': 23.01, '3326674': 3.5, '3326905': 4.5, '3327221': 4.0, '3323055': 347.68, '3329303': 38.02, '3329304': 24.01, '3332276': 44.52, '3332277': 35.52, '3334107': 40.02, '3334108': 26.01, '3337392': 32.01, '3337393': 21.01, '3340439': 40.02, '3340440': 26.01, '3343414': 32.51, '3343415': 21.01, '3346360': 4.0, '3346776': 40.52, '3346780': 27.51} | 3 | 3213061 | llmapi-tp-2gpu | 5543.396 | 16148 | 421.1721736 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.105794783 | 3.558129434 | 1 | test_unittests[llmapi-tp-2gpu] | 6 | 13 |
| 91 | test_unittests[llmapi-models-2gpu] | NVIDIA H100 NVL | 81559 | 74276 | 73436 | {'3215898': 10.44140625, '3215933': 21.50390625, '3213061': 127.8671875, '3350270': 14.25390625, '3350272': 28.6953125, '3350274': 1073.6953125, '3350431': 28.4609375, '3350536': 31875.6875, '3350537': 46400.58203125, '3355767': 10248.6796875, '3355768': 10458.0625, '3359041': 28718.64453125, '3359040': 24276.71875, '3369327': 12273.33984375, '3369328': 12054.2109375, '3376054': 25775.203125, '3376055': 26078.109375} | {'3215898': 499.71, '3215933': 499.71, '3213061': 499.71, '3350270': 0.0, '3350272': 499.21, '3350274': 499.21, '3350431': 494.21, '3350536': 131.09, '3350537': 131.59, '3355767': 43.02, '3355768': 43.52, '3359041': 123.62, '3359040': 123.62, '3369327': 83.18, '3369328': 83.18, '3376054': 107.79, '3376055': 107.79} | {'3350536': 73580.0, '3350537': 706.0, '3355767': 73122.0, '3355768': 608.0, '3359040': 73646.0, '3359041': 896.0, '3369327': 73308.0, '3376054': 73668.0, '3376055': 608.0} | {'3350536': 98.04, '3350537': 59.53, '3355767': 36.52, '3355768': 24.01, '3359040': 109.62, '3359041': 71.6, '3369327': 68.53, '3376054': 96.28, '3376055': 61.3} | 2 | 3213061 | llmapi-models-2gpu | 5543.396 | 16148 | 500.0373916 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.098053207 | 1.338635002 | 1 | test_unittests[llmapi-models-2gpu] | 5 | 5 |
| 92 | test_unittests[model-gptneox] | NVIDIA H100 NVL | 81559 | 9194 | 12978 | {'2384721': 126.98828125, '2394939': 10.32421875, '2394940': 21.9765625, '2470938': 29.37109375, '2470984': 12777.06640625, '2471144': 12.3671875} | {'2384721': 307.36, '2394939': 307.36, '2394940': 307.36, '2470938': 306.86, '2470984': 306.28, '2471144': 300.38} | {'2470984': 9194.0} | {'2470984': 278.29} | 1 | 2384721 | model-gptneox | 2149.491 | 16148 | 308.177759 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 8.870894061 | 7.574664817 | 7 | test_unittests[model-gptneox] | 0 | 6 |
| 93 | test_unittests[attention-bert] | NVIDIA H100 NVL | 81559 | 2646 | 8230 | {'2384721': 126.984375, '2394939': 10.46484375, '2394940': 21.9921875, '2496903': 13.78125, '2496906': 28.46875, '2497122': 8031.26953125, '2497622': 12.4140625} | {'2384721': 404.75, '2394939': 404.75, '2394940': 404.75, '2496903': 0.0, '2496906': 404.25, '2497122': 403.75, '2497622': 399.74} | {'2497122': 2646.0} | {'2497122': 397.74} | 1 | 2384721 | attention-bert | 2149.491 | 16148 | 405.2302971 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 30.82350718 | 11.94459295 | 11 | test_unittests[attention-bert] | 0 | 49 |
| 94 | test_unittests[model_api-part2] | NVIDIA H100 NVL | 81559 | 21854 | 27632 | {'2924976': 130.03515625, '2926291': 28.125, '2925940': 10.375, '2925941': 21.34375, '2926293': 27436.765625, '2926418': 13.28125} | {'2924976': 114.61, '2926291': 114.61, '2925940': 114.61, '2925941': 114.61, '2926293': 114.11, '2926418': 111.1} | {'2926293': 21854.0} | {'2926293': 109.6} | 1 | 2924976 | model_api-part2 | 2186.878 | 16148 | 115.4852654 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 3.731994143 | 3.55761436 | 3 | test_unittests[model_api-part2] | 0 | 1 |
| 95 | test_unittests[model-bert] | NVIDIA H100 NVL | 81559 | 3114 | 8633 | {'2924976': 129.51953125, '2925940': 10.52734375, '2928532': 21.8125, '2925941': 21.3671875, '2928569': 28.24609375, '2928573': 8437.671875, '2928702': 11.44921875} | {'2924976': 201.19, '2925940': 201.19, '2928532': 0.0, '2925941': 201.19, '2928569': 200.69, '2928573': 200.19, '2928702': 196.68} | {'2928573': 3114.0} | {'2928573': 196.18} | 1 | 2924976 | model-bert | 2186.878 | 16148 | 201.6294354 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 26.19107258 | 11.38700336 | 11 | test_unittests[model-bert] | 0 | 21 |
| 96 | test_unittests[model-gpt-e2e] | NVIDIA H100 NVL | 81559 | 3774 | 7779 | {'2924976': 129.1640625, '2945107': 23.984375, '2925940': 10.5234375, '2925941': 21.375, '2945110': 2610.09375, '2945108': 36.59375, '2945190': 11.44921875, '2945229': 1791.953125, '2945266': 10.5859375, '2945434': 7080.734375, '2945507': 10.59375, '2945691': 6402.07421875, '2945767': 10.62109375, '2946450': 988.015625, '2946526': 10.6015625, '2946583': 6392.0234375, '2946638': 10.59765625, '2946910': 6093.16796875, '2946946': 10.73046875, '2947678': 6201.0625, '2947717': 10.7265625, '2948445': 6334.33984375, '2948479': 10.58984375, '2949109': 5688.37890625, '2949187': 10.59375} | {'2924976': 202.69, '2945107': 0.0, '2925940': 202.69, '2925941': 202.69, '2945110': 202.19, '2945108': 202.19, '2945190': 199.19, '2945229': 5.0, '2945266': 2.5, '2945434': 19.02, '2945507': 16.01, '2945691': 28.03, '2945767': 25.02, '2946450': 4.0, '2946526': 1.0, '2946583': 20.52, '2946638': 17.01, '2946910': 29.03, '2946946': 26.53, '2947678': 29.53, '2947717': 26.52, '2948445': 24.02, '2948479': 21.02, '2949109': 24.02, '2949187': 21.02} | {'2945229': 990.0, '2945434': 1718.0, '2945691': 1786.0, '2946450': 1144.0, '2946583': 1720.0, '2946910': 1786.0, '2947678': 1812.0, '2948445': 1786.0, '2949109': 1812.0, '2945110': 3774.0} | {'2945229': 2.0, '2945434': 16.01, '2945691': 25.02, '2946450': 1.0, '2946583': 17.01, '2946910': 26.53, '2947678': 26.52, '2948445': 21.02, '2949109': 21.02, '2945110': 10.01} | 1 | 2924976 | model-gpt-e2e | 2186.878 | 16148 | 203.3154163 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 21.61075782 | 12.63709988 | 12 | test_unittests[model-gpt-e2e] | 0 | 1 |
| 97 | test_unittests[bindings] | NVIDIA H100 NVL | 81559 | 73318 | 8780 | {'2924976': 130.4140625, '2925940': 10.58203125, '2925941': 21.375, '2949981': 12.73828125, '2949984': 29.296875, '2949986': 3059.69140625, '2950026': 11.41015625, '2950157': 387.73828125, '2950235': 10.5859375, '2950243': 2.91015625, '2950244': 0.3515625, '2950262': 0.375, '2950260': 4.80078125, '2950283': 9.87890625, '2950355': 0.8359375, '2950356': 0.1015625, '2950357': 0.4140625, '2950362': 1766.609375, '2950438': 10.58984375, '2950554': 7078.69921875, '2950591': 10.609375, '2950845': 6389.66796875, '2950882': 10.640625, '2951553': 967.55859375, '2951642': 10.7265625, '2951665': 6292.98046875, '2951702': 10.7265625, '2951947': 5585.6875, '2952005': 10.640625, '2952702': 6032.9296875, '2952738': 10.7265625, '2953406': 6379.98046875, '2953483': 10.78125, '2953773': 6231.16796875, '2953846': 10.66015625, '2954221': 6093.83203125, '2954260': 10.60546875, '2954569': 5934.36328125, '2954605': 10.7734375, '2956099': 6313.3828125, '2956228': 10.61328125, '2956484': 6106.0, '2956559': 10.58203125, '2956806': 5778.98828125, '2956874': 10.72265625, '2957279': 5916.52734375, '2957357': 10.609375, '2957782': 2231.20703125, '2957858': 10.796875, '2958211': 5627.8046875, '2958249': 10.63671875, '2959209': 5970.4375, '2959286': 10.796875, '2960405': 2141.9140625, '2960441': 10.75390625, '2960757': 185.78515625} | {'2924976': 369.66, '2925940': 369.66, '2925941': 369.66, '2949981': 0.0, '2949984': 369.16, '2949986': 368.66, '2950026': 365.66, '2950157': 290.77, '2950235': 288.26, '2950243': 0.5, '2950244': 0.0, '2950262': 0.0, '2950260': 0.0, '2950283': 0.0, '2950355': 2.0, '2950356': 2.0, '2950357': 2.0, '2950362': 4.5, '2950438': 1.5, '2950554': 19.52, '2950591': 16.01, '2950845': 27.52, '2950882': 25.02, '2951553': 4.5, '2951642': 1.5, '2951665': 20.02, '2951702': 17.52, '2951947': 29.03, '2952005': 26.52, '2952702': 23.52, '2952738': 21.02, '2953406': 10.51, '2953483': 8.01, '2953773': 10.51, '2953846': 7.51, '2954221': 10.51, '2954260': 7.51, '2954569': 22.02, '2954605': 19.52, '2956099': 10.51, '2956228': 8.01, '2956484': 10.51, '2956559': 7.51, '2956806': 10.51, '2956874': 8.01, '2957279': 10.51, '2957357': 8.01, '2957782': 21.52, '2957858': 19.02, '2958211': 13.51, '2958249': 11.01, '2959209': 13.51, '2959286': 11.01, '2960405': 14.01, '2960441': 11.01, '2960757': 0.5} | {'2949986': 73318.0, '2950362': 990.0, '2950554': 2198.0, '2950845': 1786.0, '2951553': 1070.0, '2951665': 1718.0, '2951947': 2024.0, '2952702': 1786.0, '2953406': 1810.0, '2953773': 1810.0, '2954221': 1812.0, '2954569': 1810.0, '2956099': 2048.0, '2956484': 1812.0, '2956806': 1810.0, '2957279': 2050.0, '2957782': 1618.0, '2958211': 2078.0, '2959209': 2078.0, '2960405': 4020.0} | {'2949986': 363.15, '2950362': 1.0, '2950554': 16.51, '2950845': 25.02, '2951553': 1.0, '2951665': 17.01, '2951947': 26.02, '2952702': 21.02, '2953406': 7.51, '2953773': 7.51, '2954221': 7.51, '2954569': 19.52, '2956099': 7.51, '2956484': 8.01, '2956806': 8.01, '2957279': 8.01, '2957782': 18.52, '2958211': 10.51, '2959209': 11.01, '2960405': 10.51} | 2 | 2924976 | bindings | 2186.878 | 16148 | 370.1046725 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.112400775 | 11.19635535 | 1 | test_unittests[bindings] | 18 | 49 |
| 98 | test_unittests[llmapi-quant] | NVIDIA H100 NVL | 81559 | 73232 | 11930 | {'2924976': 130.06640625, '2972490': 17.015625, '2925940': 10.60546875, '2925941': 21.40625, '2972491': 28.375, '2972493': 11733.6328125, '2972533': 13.2734375, '2972941': 139.359375, '2972915': 1233.73828125, '2972889': 0.9765625, '2972890': 0.96484375, '2972891': 2.40234375, '2972925': 0.96484375, '2972960': 138.93359375, '2972944': 0.9609375, '2972963': 0.96484375, '2972979': 105.80078125, '2973017': 0.9609375, '2973033': 99.25, '2973034': 0.96484375, '2973050': 145.45703125, '2973069': 140.44140625, '2973053': 0.96484375, '2973122': 140.18359375, '2973106': 0.96484375, '2973124': 0.96484375, '2973140': 139.05859375, '2973159': 103.2890625, '2973143': 0.984375, '2973160': 0.9609375, '2973176': 152.046875, '2973193': 150.734375, '2973196': 17.78125, '2973177': 0.9609375, '2973197': 1947.59765625, '2973461': 2802.6484375, '2973609': 0.34765625, '2973625': 2804.48046875, '2973924': 2804.51171875, '2974098': 2803.97265625, '2974238': 27.71875, '2974254': 2803.203125, '2974486': 2803.21484375, '2974644': 2803.16015625, '2974909': 2803.0390625, '2975014': 26.63671875, '2975030': 2803.01953125, '2975256': 2803.57421875, '2975456': 1198.58203125, '2975440': 0.95703125} | {'2924976': 360.34, '2972490': 0.0, '2925940': 360.34, '2925941': 360.34, '2972491': 359.84, '2972493': 359.34, '2972533': 356.34, '2972941': 0.5, '2972915': 10.51, '2972889': 166.16, '2972890': 11.01, '2972891': 166.16, '2972925': 0.5, '2972960': 0.5, '2972944': 0.5, '2972963': 0.5, '2972979': 0.5, '2973017': 0.5, '2973033': 0.5, '2973034': 0.5, '2973050': 0.5, '2973069': 0.5, '2973053': 0.5, '2973122': 0.5, '2973106': 0.5, '2973124': 0.5, '2973140': 0.5, '2973159': 0.5, '2973143': 0.5, '2973160': 1.0, '2973176': 0.5, '2973193': 0.5, '2973196': 0.0, '2973177': 0.5, '2973197': 11.51, '2973461': 12.01, '2973609': 0.0, '2973625': 12.51, '2973924': 12.51, '2974098': 12.51, '2974238': 0.0, '2974254': 12.51, '2974486': 12.51, '2974644': 12.51, '2974909': 12.01, '2975014': 0.0, '2975030': 12.51, '2975256': 12.51, '2975456': 10.51, '2975440': 10.51} | {'2972493': 73232.0} | {'2972493': 354.84} | 1 | 2924976 | llmapi-quant | 2186.878 | 16148 | 360.6560194 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.113707123 | 8.240067058 | 1 | test_unittests[llmapi-quant] | 2 | 2 |
| 99 | test_unittests[attention-gpt-xqa-generic] | NVIDIA H100 NVL | 81559 | 12842 | 11842 | {'222016': 25.25, '203762': 126.3671875, '206211': 10.40625, '206212': 22.01171875, '222019': 33.88671875, '222023': 11638.0390625, '222247': 11.70703125} | {'222016': 0.0, '203762': 6237.65, '206211': 6237.65, '206212': 6237.65, '222019': 6237.15, '222023': 6236.65, '222247': 6232.14} | {'222023': 12842.0} | {'222023': 6230.14} | 1 | 203762 | attention-gpt-xqa-generic | 7981.589 | 16148 | 6238.164207 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 6.350957795 | 8.301300456 | 6 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |
| 100 | test_unittests[functional-moe] | NVIDIA H100 NVL | 81559 | 4788 | 9346 | {'203762': 127.22265625, '206211': 10.48828125, '206212': 22.0078125, '705621': 24.48046875, '705624': 28.72265625, '705626': 9146.296875, '705784': 11.6953125} | {'203762': 788.86, '206211': 788.86, '206212': 788.86, '705621': 0.0, '705624': 788.36, '705626': 787.86, '705784': 783.35} | {'705626': 4788.0} | {'705626': 781.85} | 1 | 203762 | functional-moe | 7981.589 | 16148 | 789.6104999 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 17.03404344 | 10.5182966 | 10 | test_unittests[functional-moe] | 0 | 82 |
| 101 | test_unittests[unit-woq-percol] | NVIDIA H100 NVL | 81559 | 2208 | 7275 | {'203762': 127.1875, '206211': 10.49609375, '206212': 22.0078125, '940916': 28.22265625, '940919': 7075.88671875, '941171': 11.6953125} | {'203762': 141.11, '206211': 141.11, '206212': 141.11, '940916': 140.61, '940919': 140.11, '941171': 135.6} | {'940919': 2208.0} | {'940919': 133.6} | 1 | 203762 | unit-woq-percol | 7981.589 | 16148 | 141.2499655 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 36.9379529 | 13.51257732 | 13 | test_unittests[unit-woq-percol] | 0 | 18 |
| 102 | test_unittests[unit-woq-group] | NVIDIA H100 NVL | 81559 | 1922 | 7544 | {'203762': 127.1875, '206211': 10.51171875, '206212': 22.0078125, '957533': 25.69921875, '957546': 28.4921875, '957550': 7345.2265625, '957751': 11.70703125} | {'203762': 288.27, '206211': 288.27, '206212': 288.27, '957533': 0.0, '957546': 287.77, '957550': 287.27, '957751': 283.27} | {'957550': 1922.0} | {'957550': 281.27} | 1 | 203762 | unit-woq-group | 7981.589 | 16148 | 288.8596221 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 42.43444329 | 13.03075292 | 13 | test_unittests[unit-woq-group] | 0 | 50 |
| 103 | test_unittests[attention-gpt-plugin-ib-mode] | NVIDIA H100 NVL | 81559 | 2216 | 8471 | {'1865': 10.28125, '786': 130.33984375, '1866': 21.41796875, '2039': 19.18359375, '2040': 31.39453125, '2044': 8270.97265625, '2215': 13.2109375} | {'1865': 191.17, '786': 191.17, '1866': 191.17, '2039': 0.0, '2040': 190.67, '2044': 190.17, '2215': 187.17} | {'2044': 2216.0} | {'2044': 185.67} | 1 | 786 | attention-gpt-plugin-ib-mode | 1530.122 | 16148 | 191.7125493 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 36.80460289 | 11.60476921 | 11 | test_unittests[attention-gpt-plugin-ib-mode] | 0 | 34 |
| 104 | test_unittests[attention-gpt-no-cache] | NVIDIA H100 NVL | 81559 | 1946 | 7393 | {'1865': 10.390625, '786': 131.29296875, '1866': 21.484375, '9534': 11.859375, '9584': 28.15625, '9587': 7196.453125, '9659': 13.1953125} | {'1865': 21.02, '786': 21.02, '1866': 21.02, '9534': 0.0, '9584': 20.52, '9587': 20.02, '9659': 17.02} | {'9587': 1946.0} | {'9587': 16.02} | 1 | 786 | attention-gpt-no-cache | 1530.122 | 16148 | 21.58346564 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 41.91109969 | 13.29690248 | 13 | test_unittests[attention-gpt-no-cache] | 0 | 2 |
| 105 | test_unittests[model-mamba] | NVIDIA H100 NVL | 81559 | 2096 | 9791 | {'1865': 10.48046875, '786': 131.66796875, '19549': 45.97265625, '1866': 21.5078125, '19597': 12.453125, '19598': 28.2421875, '19602': 9593.8515625, '19642': 13.17578125} | {'1865': 321.3, '786': 321.3, '19549': 1.0, '1866': 321.3, '19597': 0.0, '19598': 319.3, '19602': 318.8, '19642': 315.8} | {'19602': 2096.0} | {'19602': 291.27} | 1 | 786 | model-mamba | 1530.122 | 16148 | 322.2435047 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 38.91173664 | 10.04024104 | 10 | test_unittests[model-mamba] | 0 | 12 |
| 106 | test_unittests[llmapi-tp-2gpu] | NVIDIA H100 | 81559 | 73756 | 27628 | {'3215898': 10.3359375, '3215933': 21.49609375, '3213061': 130.5, '3323042': 30.0546875, '3323055': 12172.48828125, '3323325': 29.2265625, '3323842': 8266.75390625, '3323843': 8935.0859375, '3326674': 2611.1953125, '3326675': 2611.8046875, '3326906': 2605.125, '3326905': 2607.7578125, '3327221': 2596.72265625, '3327222': 2596.32421875, '3329303': 8834.60546875, '3329304': 8454.85546875, '3332276': 8050.3359375, '3332277': 9001.72265625, '3334107': 8570.27734375, '3334108': 8940.27734375, '3337392': 8802.87109375, '3337393': 9091.703125, '3340439': 8662.23046875, '3340440': 8963.91796875, '3343414': 8724.72265625, '3343415': 8828.78515625, '3346319': 11.6875, '3346336': 0.3828125, '3346337': 0.37890625, '3346360': 2604.953125, '3346366': 2609.21875, '3346776': 8781.49609375, '3346780': 8883.0} | {'3215898': 420.74, '3215933': 420.74, '3213061': 420.74, '3323042': 420.24, '3323055': 419.74, '3323325': 414.73, '3323842': 40.53, '3323843': 41.53, '3326674': 7.51, '3326675': 7.51, '3326906': 9.51, '3326905': 9.51, '3327221': 7.51, '3327222': 7.51, '3329303': 43.02, '3329304': 43.02, '3332276': 49.03, '3332277': 49.03, '3334107': 45.52, '3334108': 46.02, '3337392': 36.52, '3337393': 37.02, '3340439': 45.52, '3340440': 46.52, '3343414': 37.02, '3343415': 37.52, '3346319': 12.01, '3346336': 11.51, '3346337': 11.51, '3346360': 11.51, '3346366': 11.51, '3346776': 45.02, '3346780': 45.02} | {'3323842': 3074.0, '3323843': 610.0, '3326674': 73454.0, '3326905': 34118.0, '3327221': 34118.0, '3323055': 4062.0, '3329303': 34332.0, '3329304': 896.0, '3332276': 33510.0, '3332277': 608.0, '3334107': 72426.0, '3334108': 896.0, '3337392': 72432.0, '3337393': 896.0, '3340439': 72422.0, '3340440': 896.0, '3343414': 72492.0, '3343415': 608.0, '3346360': 72858.0, '3346776': 34398.0, '3346780': 610.0} | {'3323842': 35.52, '3323843': 23.01, '3326674': 3.5, '3326905': 4.5, '3327221': 4.0, '3323055': 347.68, '3329303': 38.02, '3329304': 24.01, '3332276': 44.52, '3332277': 35.52, '3334107': 40.02, '3334108': 26.01, '3337392': 32.01, '3337393': 21.01, '3340439': 40.02, '3340440': 26.01, '3343414': 32.51, '3343415': 21.01, '3346360': 4.0, '3346776': 40.52, '3346780': 27.51} | 3 | 3213061 | llmapi-tp-2gpu | 5543.396 | 16148 | 421.1721736 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.105794783 | 3.558129434 | 1 | test_unittests[llmapi-tp-2gpu] | 6 | 13 |
| 107 | test_unittests[llmapi-models-2gpu] | NVIDIA H100 | 81559 | 74276 | 73436 | {'3215898': 10.44140625, '3215933': 21.50390625, '3213061': 127.8671875, '3350270': 14.25390625, '3350272': 28.6953125, '3350274': 1073.6953125, '3350431': 28.4609375, '3350536': 31875.6875, '3350537': 46400.58203125, '3355767': 10248.6796875, '3355768': 10458.0625, '3359041': 28718.64453125, '3359040': 24276.71875, '3369327': 12273.33984375, '3369328': 12054.2109375, '3376054': 25775.203125, '3376055': 26078.109375} | {'3215898': 499.71, '3215933': 499.71, '3213061': 499.71, '3350270': 0.0, '3350272': 499.21, '3350274': 499.21, '3350431': 494.21, '3350536': 131.09, '3350537': 131.59, '3355767': 43.02, '3355768': 43.52, '3359041': 123.62, '3359040': 123.62, '3369327': 83.18, '3369328': 83.18, '3376054': 107.79, '3376055': 107.79} | {'3350536': 73580.0, '3350537': 706.0, '3355767': 73122.0, '3355768': 608.0, '3359040': 73646.0, '3359041': 896.0, '3369327': 73308.0, '3376054': 73668.0, '3376055': 608.0} | {'3350536': 98.04, '3350537': 59.53, '3355767': 36.52, '3355768': 24.01, '3359040': 109.62, '3359041': 71.6, '3369327': 68.53, '3376054': 96.28, '3376055': 61.3} | 2 | 3213061 | llmapi-models-2gpu | 5543.396 | 16148 | 500.0373916 | E2E Tests (multi-GPU) on DGX-H100 4 GPUs | [E2E Tests (multi-GPU) on DGX-H100 4 GPUs] Run TURTLE | 1.098053207 | 1.338635002 | 1 | test_unittests[llmapi-models-2gpu] | 5 | 5 |
| 108 | test_unittests[model-gptneox] | NVIDIA H100 | 81559 | 9194 | 12978 | {'2384721': 126.98828125, '2394939': 10.32421875, '2394940': 21.9765625, '2470938': 29.37109375, '2470984': 12777.06640625, '2471144': 12.3671875} | {'2384721': 307.36, '2394939': 307.36, '2394940': 307.36, '2470938': 306.86, '2470984': 306.28, '2471144': 300.38} | {'2470984': 9194.0} | {'2470984': 278.29} | 1 | 2384721 | model-gptneox | 2149.491 | 16148 | 308.177759 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 8.870894061 | 7.574664817 | 7 | test_unittests[model-gptneox] | 0 | 6 |
| 109 | test_unittests[attention-bert] | NVIDIA H100 | 81559 | 2646 | 8230 | {'2384721': 126.984375, '2394939': 10.46484375, '2394940': 21.9921875, '2496903': 13.78125, '2496906': 28.46875, '2497122': 8031.26953125, '2497622': 12.4140625} | {'2384721': 404.75, '2394939': 404.75, '2394940': 404.75, '2496903': 0.0, '2496906': 404.25, '2497122': 403.75, '2497622': 399.74} | {'2497122': 2646.0} | {'2497122': 397.74} | 1 | 2384721 | attention-bert | 2149.491 | 16148 | 405.2302971 | H100_PCIe-accuracy-1 | [H100_PCIe-accuracy-1] Run TURTLE | 30.82350718 | 11.94459295 | 11 | test_unittests[attention-bert] | 0 | 49 |
| 110 | test_unittests[model_api-part2] | NVIDIA H100 | 81559 | 21854 | 27632 | {'2924976': 130.03515625, '2926291': 28.125, '2925940': 10.375, '2925941': 21.34375, '2926293': 27436.765625, '2926418': 13.28125} | {'2924976': 114.61, '2926291': 114.61, '2925940': 114.61, '2925941': 114.61, '2926293': 114.11, '2926418': 111.1} | {'2926293': 21854.0} | {'2926293': 109.6} | 1 | 2924976 | model_api-part2 | 2186.878 | 16148 | 115.4852654 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 3.731994143 | 3.55761436 | 3 | test_unittests[model_api-part2] | 0 | 1 |
| 111 | test_unittests[model-bert] | NVIDIA H100 | 81559 | 3114 | 8633 | {'2924976': 129.51953125, '2925940': 10.52734375, '2928532': 21.8125, '2925941': 21.3671875, '2928569': 28.24609375, '2928573': 8437.671875, '2928702': 11.44921875} | {'2924976': 201.19, '2925940': 201.19, '2928532': 0.0, '2925941': 201.19, '2928569': 200.69, '2928573': 200.19, '2928702': 196.68} | {'2928573': 3114.0} | {'2928573': 196.18} | 1 | 2924976 | model-bert | 2186.878 | 16148 | 201.6294354 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 26.19107258 | 11.38700336 | 11 | test_unittests[model-bert] | 0 | 21 |
| 112 | test_unittests[model-gpt-e2e] | NVIDIA H100 | 81559 | 3774 | 7779 | {'2924976': 129.1640625, '2945107': 23.984375, '2925940': 10.5234375, '2925941': 21.375, '2945110': 2610.09375, '2945108': 36.59375, '2945190': 11.44921875, '2945229': 1791.953125, '2945266': 10.5859375, '2945434': 7080.734375, '2945507': 10.59375, '2945691': 6402.07421875, '2945767': 10.62109375, '2946450': 988.015625, '2946526': 10.6015625, '2946583': 6392.0234375, '2946638': 10.59765625, '2946910': 6093.16796875, '2946946': 10.73046875, '2947678': 6201.0625, '2947717': 10.7265625, '2948445': 6334.33984375, '2948479': 10.58984375, '2949109': 5688.37890625, '2949187': 10.59375} | {'2924976': 202.69, '2945107': 0.0, '2925940': 202.69, '2925941': 202.69, '2945110': 202.19, '2945108': 202.19, '2945190': 199.19, '2945229': 5.0, '2945266': 2.5, '2945434': 19.02, '2945507': 16.01, '2945691': 28.03, '2945767': 25.02, '2946450': 4.0, '2946526': 1.0, '2946583': 20.52, '2946638': 17.01, '2946910': 29.03, '2946946': 26.53, '2947678': 29.53, '2947717': 26.52, '2948445': 24.02, '2948479': 21.02, '2949109': 24.02, '2949187': 21.02} | {'2945229': 990.0, '2945434': 1718.0, '2945691': 1786.0, '2946450': 1144.0, '2946583': 1720.0, '2946910': 1786.0, '2947678': 1812.0, '2948445': 1786.0, '2949109': 1812.0, '2945110': 3774.0} | {'2945229': 2.0, '2945434': 16.01, '2945691': 25.02, '2946450': 1.0, '2946583': 17.01, '2946910': 26.53, '2947678': 26.52, '2948445': 21.02, '2949109': 21.02, '2945110': 10.01} | 1 | 2924976 | model-gpt-e2e | 2186.878 | 16148 | 203.3154163 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 21.61075782 | 12.63709988 | 12 | test_unittests[model-gpt-e2e] | 0 | 1 |
| 113 | test_unittests[bindings] | NVIDIA H100 | 81559 | 73318 | 8780 | {'2924976': 130.4140625, '2925940': 10.58203125, '2925941': 21.375, '2949981': 12.73828125, '2949984': 29.296875, '2949986': 3059.69140625, '2950026': 11.41015625, '2950157': 387.73828125, '2950235': 10.5859375, '2950243': 2.91015625, '2950244': 0.3515625, '2950262': 0.375, '2950260': 4.80078125, '2950283': 9.87890625, '2950355': 0.8359375, '2950356': 0.1015625, '2950357': 0.4140625, '2950362': 1766.609375, '2950438': 10.58984375, '2950554': 7078.69921875, '2950591': 10.609375, '2950845': 6389.66796875, '2950882': 10.640625, '2951553': 967.55859375, '2951642': 10.7265625, '2951665': 6292.98046875, '2951702': 10.7265625, '2951947': 5585.6875, '2952005': 10.640625, '2952702': 6032.9296875, '2952738': 10.7265625, '2953406': 6379.98046875, '2953483': 10.78125, '2953773': 6231.16796875, '2953846': 10.66015625, '2954221': 6093.83203125, '2954260': 10.60546875, '2954569': 5934.36328125, '2954605': 10.7734375, '2956099': 6313.3828125, '2956228': 10.61328125, '2956484': 6106.0, '2956559': 10.58203125, '2956806': 5778.98828125, '2956874': 10.72265625, '2957279': 5916.52734375, '2957357': 10.609375, '2957782': 2231.20703125, '2957858': 10.796875, '2958211': 5627.8046875, '2958249': 10.63671875, '2959209': 5970.4375, '2959286': 10.796875, '2960405': 2141.9140625, '2960441': 10.75390625, '2960757': 185.78515625} | {'2924976': 369.66, '2925940': 369.66, '2925941': 369.66, '2949981': 0.0, '2949984': 369.16, '2949986': 368.66, '2950026': 365.66, '2950157': 290.77, '2950235': 288.26, '2950243': 0.5, '2950244': 0.0, '2950262': 0.0, '2950260': 0.0, '2950283': 0.0, '2950355': 2.0, '2950356': 2.0, '2950357': 2.0, '2950362': 4.5, '2950438': 1.5, '2950554': 19.52, '2950591': 16.01, '2950845': 27.52, '2950882': 25.02, '2951553': 4.5, '2951642': 1.5, '2951665': 20.02, '2951702': 17.52, '2951947': 29.03, '2952005': 26.52, '2952702': 23.52, '2952738': 21.02, '2953406': 10.51, '2953483': 8.01, '2953773': 10.51, '2953846': 7.51, '2954221': 10.51, '2954260': 7.51, '2954569': 22.02, '2954605': 19.52, '2956099': 10.51, '2956228': 8.01, '2956484': 10.51, '2956559': 7.51, '2956806': 10.51, '2956874': 8.01, '2957279': 10.51, '2957357': 8.01, '2957782': 21.52, '2957858': 19.02, '2958211': 13.51, '2958249': 11.01, '2959209': 13.51, '2959286': 11.01, '2960405': 14.01, '2960441': 11.01, '2960757': 0.5} | {'2949986': 73318.0, '2950362': 990.0, '2950554': 2198.0, '2950845': 1786.0, '2951553': 1070.0, '2951665': 1718.0, '2951947': 2024.0, '2952702': 1786.0, '2953406': 1810.0, '2953773': 1810.0, '2954221': 1812.0, '2954569': 1810.0, '2956099': 2048.0, '2956484': 1812.0, '2956806': 1810.0, '2957279': 2050.0, '2957782': 1618.0, '2958211': 2078.0, '2959209': 2078.0, '2960405': 4020.0} | {'2949986': 363.15, '2950362': 1.0, '2950554': 16.51, '2950845': 25.02, '2951553': 1.0, '2951665': 17.01, '2951947': 26.02, '2952702': 21.02, '2953406': 7.51, '2953773': 7.51, '2954221': 7.51, '2954569': 19.52, '2956099': 7.51, '2956484': 8.01, '2956806': 8.01, '2957279': 8.01, '2957782': 18.52, '2958211': 10.51, '2959209': 11.01, '2960405': 10.51} | 2 | 2924976 | bindings | 2186.878 | 16148 | 370.1046725 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.112400775 | 11.19635535 | 1 | test_unittests[bindings] | 18 | 49 |
| 114 | test_unittests[llmapi-quant] | NVIDIA H100 | 81559 | 73232 | 11930 | {'2924976': 130.06640625, '2972490': 17.015625, '2925940': 10.60546875, '2925941': 21.40625, '2972491': 28.375, '2972493': 11733.6328125, '2972533': 13.2734375, '2972941': 139.359375, '2972915': 1233.73828125, '2972889': 0.9765625, '2972890': 0.96484375, '2972891': 2.40234375, '2972925': 0.96484375, '2972960': 138.93359375, '2972944': 0.9609375, '2972963': 0.96484375, '2972979': 105.80078125, '2973017': 0.9609375, '2973033': 99.25, '2973034': 0.96484375, '2973050': 145.45703125, '2973069': 140.44140625, '2973053': 0.96484375, '2973122': 140.18359375, '2973106': 0.96484375, '2973124': 0.96484375, '2973140': 139.05859375, '2973159': 103.2890625, '2973143': 0.984375, '2973160': 0.9609375, '2973176': 152.046875, '2973193': 150.734375, '2973196': 17.78125, '2973177': 0.9609375, '2973197': 1947.59765625, '2973461': 2802.6484375, '2973609': 0.34765625, '2973625': 2804.48046875, '2973924': 2804.51171875, '2974098': 2803.97265625, '2974238': 27.71875, '2974254': 2803.203125, '2974486': 2803.21484375, '2974644': 2803.16015625, '2974909': 2803.0390625, '2975014': 26.63671875, '2975030': 2803.01953125, '2975256': 2803.57421875, '2975456': 1198.58203125, '2975440': 0.95703125} | {'2924976': 360.34, '2972490': 0.0, '2925940': 360.34, '2925941': 360.34, '2972491': 359.84, '2972493': 359.34, '2972533': 356.34, '2972941': 0.5, '2972915': 10.51, '2972889': 166.16, '2972890': 11.01, '2972891': 166.16, '2972925': 0.5, '2972960': 0.5, '2972944': 0.5, '2972963': 0.5, '2972979': 0.5, '2973017': 0.5, '2973033': 0.5, '2973034': 0.5, '2973050': 0.5, '2973069': 0.5, '2973053': 0.5, '2973122': 0.5, '2973106': 0.5, '2973124': 0.5, '2973140': 0.5, '2973159': 0.5, '2973143': 0.5, '2973160': 1.0, '2973176': 0.5, '2973193': 0.5, '2973196': 0.0, '2973177': 0.5, '2973197': 11.51, '2973461': 12.01, '2973609': 0.0, '2973625': 12.51, '2973924': 12.51, '2974098': 12.51, '2974238': 0.0, '2974254': 12.51, '2974486': 12.51, '2974644': 12.51, '2974909': 12.01, '2975014': 0.0, '2975030': 12.51, '2975256': 12.51, '2975456': 10.51, '2975440': 10.51} | {'2972493': 73232.0} | {'2972493': 354.84} | 1 | 2924976 | llmapi-quant | 2186.878 | 16148 | 360.6560194 | H100_PCIe-others-0 | [H100_PCIe-others-0] Run TURTLE | 1.113707123 | 8.240067058 | 1 | test_unittests[llmapi-quant] | 2 | 2 |
| 115 | test_unittests[attention-gpt-xqa-generic] | NVIDIA H100 | 81559 | 12842 | 11842 | {'222016': 25.25, '203762': 126.3671875, '206211': 10.40625, '206212': 22.01171875, '222019': 33.88671875, '222023': 11638.0390625, '222247': 11.70703125} | {'222016': 0.0, '203762': 6237.65, '206211': 6237.65, '206212': 6237.65, '222019': 6237.15, '222023': 6236.65, '222247': 6232.14} | {'222023': 12842.0} | {'222023': 6230.14} | 1 | 203762 | attention-gpt-xqa-generic | 7981.589 | 16148 | 6238.164207 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 6.350957795 | 8.301300456 | 6 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |
| 116 | test_unittests[functional-moe] | NVIDIA H100 | 81559 | 4788 | 9346 | {'203762': 127.22265625, '206211': 10.48828125, '206212': 22.0078125, '705621': 24.48046875, '705624': 28.72265625, '705626': 9146.296875, '705784': 11.6953125} | {'203762': 788.86, '206211': 788.86, '206212': 788.86, '705621': 0.0, '705624': 788.36, '705626': 787.86, '705784': 783.35} | {'705626': 4788.0} | {'705626': 781.85} | 1 | 203762 | functional-moe | 7981.589 | 16148 | 789.6104999 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 17.03404344 | 10.5182966 | 10 | test_unittests[functional-moe] | 0 | 82 |
| 117 | test_unittests[unit-woq-percol] | NVIDIA H100 | 81559 | 2208 | 7275 | {'203762': 127.1875, '206211': 10.49609375, '206212': 22.0078125, '940916': 28.22265625, '940919': 7075.88671875, '941171': 11.6953125} | {'203762': 141.11, '206211': 141.11, '206212': 141.11, '940916': 140.61, '940919': 140.11, '941171': 135.6} | {'940919': 2208.0} | {'940919': 133.6} | 1 | 203762 | unit-woq-percol | 7981.589 | 16148 | 141.2499655 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 36.9379529 | 13.51257732 | 13 | test_unittests[unit-woq-percol] | 0 | 18 |
| 118 | test_unittests[unit-woq-group] | NVIDIA H100 | 81559 | 1922 | 7544 | {'203762': 127.1875, '206211': 10.51171875, '206212': 22.0078125, '957533': 25.69921875, '957546': 28.4921875, '957550': 7345.2265625, '957751': 11.70703125} | {'203762': 288.27, '206211': 288.27, '206212': 288.27, '957533': 0.0, '957546': 287.77, '957550': 287.27, '957751': 283.27} | {'957550': 1922.0} | {'957550': 281.27} | 1 | 203762 | unit-woq-group | 7981.589 | 16148 | 288.8596221 | H100_PCIe-unittests | [H100_PCIe-unittests] Run TURTLE | 42.43444329 | 13.03075292 | 13 | test_unittests[unit-woq-group] | 0 | 50 |
| 119 | test_unittests[attention-gpt-plugin-ib-mode] | NVIDIA H100 | 81559 | 2216 | 8471 | {'1865': 10.28125, '786': 130.33984375, '1866': 21.41796875, '2039': 19.18359375, '2040': 31.39453125, '2044': 8270.97265625, '2215': 13.2109375} | {'1865': 191.17, '786': 191.17, '1866': 191.17, '2039': 0.0, '2040': 190.67, '2044': 190.17, '2215': 187.17} | {'2044': 2216.0} | {'2044': 185.67} | 1 | 786 | attention-gpt-plugin-ib-mode | 1530.122 | 16148 | 191.7125493 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 36.80460289 | 11.60476921 | 11 | test_unittests[attention-gpt-plugin-ib-mode] | 0 | 34 |
| 120 | test_unittests[attention-gpt-no-cache] | NVIDIA H100 | 81559 | 1946 | 7393 | {'1865': 10.390625, '786': 131.29296875, '1866': 21.484375, '9534': 11.859375, '9584': 28.15625, '9587': 7196.453125, '9659': 13.1953125} | {'1865': 21.02, '786': 21.02, '1866': 21.02, '9534': 0.0, '9584': 20.52, '9587': 20.02, '9659': 17.02} | {'9587': 1946.0} | {'9587': 16.02} | 1 | 786 | attention-gpt-no-cache | 1530.122 | 16148 | 21.58346564 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 41.91109969 | 13.29690248 | 13 | test_unittests[attention-gpt-no-cache] | 0 | 2 |
| 121 | test_unittests[model-mamba] | NVIDIA H100 | 81559 | 2096 | 9791 | {'1865': 10.48046875, '786': 131.66796875, '19549': 45.97265625, '1866': 21.5078125, '19597': 12.453125, '19598': 28.2421875, '19602': 9593.8515625, '19642': 13.17578125} | {'1865': 321.3, '786': 321.3, '19549': 1.0, '1866': 321.3, '19597': 0.0, '19598': 319.3, '19602': 318.8, '19642': 315.8} | {'19602': 2096.0} | {'19602': 291.27} | 1 | 786 | model-mamba | 1530.122 | 16148 | 322.2435047 | H100_PCIe-accuracy-2 | [H100_PCIe-accuracy-2] Run TURTLE | 38.91173664 | 10.04024104 | 10 | test_unittests[model-mamba] | 0 | 12 |
| 122 | test_unittests[attention-gpt-partition0] | NVIDIA L40 | 46068 | 2622 | 6678 | {'3592777': 10.26953125, '3575269': 125.5703125, '3592791': 21.91796875, '3593032': 25.24609375, '3593046': 30.125, '3593140': 6480.46484375, '3593572': 11.703125} | {'3592777': 241.47, '3575269': 241.47, '3592791': 241.47, '3593032': 0.0, '3593046': 240.46, '3593140': 239.46, '3593572': 234.46} | {'3593140': 2622.0} | {'3593140': 231.88} | 1 | 3575269 | attention-gpt-partition0 | 4105.914 | 16148 | 241.3219729 | L40S-unittests | [L40S-unittests] Run TURTLE | 17.56979405 | 14.72057502 | 14 | test_unittests[attention-gpt-partition0] | 0 | 67 |
| 123 | test_unittests[attention-gpt-partition1] | NVIDIA L40 | 46068 | 4240 | 6669 | {'3592777': 10.41015625, '3575269': 124.58203125, '3592791': 21.91796875, '3629421': 6472.44921875, '3629404': 28.7109375, '3629626': 11.6953125} | {'3592777': 251.95, '3575269': 251.95, '3592791': 251.95, '3629421': 251.45, '3629404': 251.45, '3629626': 246.94} | {'3629421': 4240.0} | {'3629421': 244.44} | 1 | 3575269 | attention-gpt-partition1 | 4105.914 | 16148 | 252.5983796 | L40S-unittests | [L40S-unittests] Run TURTLE | 10.86509434 | 14.74044085 | 10 | test_unittests[attention-gpt-partition1] | 0 | 65 |
| 124 | test_unittests[attention-gpt-partition2] | NVIDIA L40 | 46068 | 7496 | 6726 | {'3592777': 10.4453125, '3651794': 25.24609375, '3575269': 124.5859375, '3592791': 21.9375, '3651821': 29.83984375, '3651842': 6529.80078125, '3652053': 11.69921875} | {'3592777': 222.64, '3651794': 0.0, '3575269': 222.64, '3592791': 222.64, '3651821': 222.14, '3651842': 221.14, '3652053': 217.14} | {'3651842': 7496.0} | {'3651842': 214.13} | 1 | 3575269 | attention-gpt-partition2 | 4105.914 | 16148 | 222.9654428 | L40S-unittests | [L40S-unittests] Run TURTLE | 6.145677695 | 14.61552186 | 6 | test_unittests[attention-gpt-partition2] | 0 | 66 |
| 125 | test_unittests[attention-gpt-partition3] | NVIDIA L40 | 46068 | 7492 | 6706 | {'3592777': 10.47265625, '3673329': 28.80859375, '3575269': 124.59375, '3592791': 21.9453125, '3673333': 6508.796875, '3673469': 11.69921875} | {'3592777': 229.63, '3673329': 229.63, '3575269': 229.63, '3592791': 229.63, '3673333': 229.13, '3673469': 224.13} | {'3673333': 7492.0} | {'3673333': 221.62} | 1 | 3575269 | attention-gpt-partition3 | 4105.914 | 16148 | 230.4534084 | L40S-unittests | [L40S-unittests] Run TURTLE | 6.148958889 | 14.65911124 | 6 | test_unittests[attention-gpt-partition3] | 0 | 65 |
| 126 | test_unittests[attention-gpt-xqa-generic] | NVIDIA L40 | 46068 | 12008 | 8760 | {'3592777': 10.50390625, '3575269': 124.59375, '3592791': 21.9375, '3691567': 18.91015625, '3691568': 33.0625, '3691570': 8558.125, '3691800': 12.484375} | {'3592777': 3018.28, '3575269': 3018.28, '3592791': 3018.28, '3691567': 0.0, '3691568': 3017.78, '3691570': 3017.28, '3691800': 3013.27} | {'3691570': 12008.0} | {'3691570': 3011.27} | 1 | 3575269 | attention-gpt-xqa-generic | 4105.914 | 16148 | 3018.694419 | L40S-unittests | [L40S-unittests] Run TURTLE | 3.836442372 | 11.22191781 | 3 | test_unittests[attention-gpt-xqa-generic] | 0 | 540 |