..
accuracy
[ https://nvbugs/5674665 ][fix] Fix accuracy drop in VSWA with KV cache block reuse ( #10875 )
2026-02-04 12:46:31 -05:00
cpp
[ https://nvbugs/5630196 ] [fix] Prevent flaky failures in C++ test_e2e.py by using local cached datasets for benchmarking ( #10638 )
2026-01-14 21:39:55 -05:00
deterministic
[ https://nvbugs/4141427 ][chore] Add more details to LICENSE file ( #9881 )
2025-12-13 08:35:31 +08:00
disaggregated
[ https://nvbugs/5821433 ][fix] fix test_auto_scaling for 2 GPUs ( #10866 )
2026-02-02 16:26:46 +08:00
examples
[ #10826 ][feat] AutoDeploy: Eagle One-Model [2/n]: Prefill-Only Implementation ( #11073 )
2026-02-02 09:51:10 -08:00
llmapi
[None][feat] Add priority-based KV cache offload filtering support ( #10751 )
2026-02-05 05:22:56 -05:00
perf
[TRTLLM-8263][feat] Add Disagg Perf Tests ( #10912 )
2026-02-04 10:16:11 +08:00
ray_orchestrator /RL
[TRTLLM-9737][chore] Add rl perf reproduce script and enhance the robustness of Ray tests ( #9939 )
2025-12-24 15:27:01 +08:00
stress_test
[ https://nvbugs/5814203 ][fix] Fix port 8000 being used issue in stress test. ( #10756 )
2026-01-25 18:12:21 +08:00
sysinfo
[None][infra] Enable single-gpu CI on spark ( #9304 )
2025-12-30 17:22:14 +08:00
thirdparty
[TRTLLM-9228][infra] Verify thirdparty C++ process ( #9367 )
2025-12-10 21:01:19 +08:00
triton_server
[None][feat] Expose enable_trt_overlap in Triton_backend brings 1.05x OTPS ( #10018 )
2025-12-23 11:41:31 -06:00
utils
[TRTLLM-7181][infra] Generate test results when pytest timeout happens ( #9396 )
2025-12-04 10:05:38 +08:00
__init__.py
[fix] Remove SpecConfig and fix thread leak issues ( #5931 )
2025-07-12 21:03:24 +09:00
.test_durations
[TRTLLM-9766][feat] Integration of the KVCacheManager V2 to TRTLLM Runtime ( #10659 )
2026-02-02 14:29:02 +08:00
agg_unit_mem_df.csv
[TRTLLM-7738][feat] Adding implementation of KVCacheManagerV2 ( #10736 )
2026-01-24 04:48:39 -05:00
ci_profiler.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
common.py
[ https://nvbugs/5760726 ][fix] Use random port in container port section ( #10432 )
2026-01-06 23:25:46 +08:00
conftest.py
[TRTLLM-9581][infra] Use /home/scratch.trt_llm_data_ci in computelab ( #10616 )
2026-01-19 00:40:40 -05:00
local_venv.py
[TRTLLM-5950][infra] Removing remaining turtle keywords from the code base ( #7086 )
2025-09-07 14:26:18 +08:00
pytest.ini
[TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic ( #9726 )
2025-12-16 05:16:32 -08:00
runner_interface.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
test_cases.yml
Update ( #2978 )
2025-03-23 16:39:35 +08:00
test_e2e.py
[ https://nvbugs/5837281 ][fix] Fix trtllm-serve guided decoding test ( #11101 )
2026-01-30 16:59:55 +08:00
test_fmha.py
[TRTLLM-9805][feat] Skip Softmax Attention. ( #9821 )
2025-12-21 02:52:42 -05:00
test_list_parser.py
[None][feat] add waive by sm version ( #8928 )
2025-11-05 19:20:43 -08:00
test_list_validation.py
[Infra]Remove some old keyword ( #4552 )
2025-05-31 13:50:45 +08:00
test_mlpf_results.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
test_sanity.py
Update ( #2978 )
2025-03-23 16:39:35 +08:00
test_unittests.py
[TRTLLM-9642][infra] Increase pytest verbosity for failed tests ( #9657 )
2026-01-08 02:33:48 -05:00
trt_test_alternative.py
[TRTLLM-7349][feat] Adding new orchestrator type -- ray ( #7520 )
2025-10-04 08:12:24 +08:00
0d18b2d7a4