kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

test: add qwen3 and disaggregated serving accuracy tests to qa test list (#4083)

Browse Source 
Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
This commit is contained in:
Stanley Sun 2025-05-09 11:03:02 +08:00 committed by GitHub
parent 5b61486d87
commit fb31f91e15
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/integration/test_lists/qa/examples_test_list.txt
View File

@ -445,6 +445,10 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep4---cuda
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep4-mtp_nextn=2--cuda_graph-overlap_scheduler]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep8---cuda_graph-overlap_scheduler]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep8-mtp_nextn=2--cuda_graph-overlap_scheduler]
accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency]
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8_block_scales[latency]
accuracy/test_disaggregated_serving.py::TestLlama3_1_8B::test_auto_dtype[False]
accuracy/test_disaggregated_serving.py::TestLlama3_1_8B::test_auto_dtype[True]
test_e2e.py::test_benchmark_sanity[bert_base] # 127.18s
test_e2e.py::test_benchmark_sanity[gpt_350m] # 64.06s