kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-05 10:42:38 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][test] Update case for release (#10811)

Browse Source 
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit is contained in:
Ivy Zhang 2026-01-21 10:36:53 +08:00 committed by Yanchao Lu
parent 18f63dfcec
commit bcd2dc490c
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -5104,7 +5104,7 @@ class TestDeepSeekR1LongBenchV2(LlmapiAccuracyTestHarness):
pytest.skip(f"Model directory {model_dir} does not exist")
# Configure model settings
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.8,
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.4,
enable_block_reuse=True,
enable_partial_reuse=False,
dtype="fp8")

2
tests/integration/test_lists/qa/llm_function_core.txt
View File

@ -119,6 +119,8 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp_trtllm]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale_chunked_prefill[latency]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale_chunked_prefill[throughput]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1LongBenchV2::test_fp8_8gpus TIMEOUT (240)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1LongBenchV2::test_nvfp4_4gpus TIMEOUT (240)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline_mtp1]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline_fp8kv]

2
tests/integration/test_lists/qa/llm_function_stress.txt
View File

@ -3,5 +3,3 @@ stress_test/stress_test.py::test_run_stress_test[DeepSeek-V3_tp8-stress_time_360
stress_test/stress_test.py::test_run_stress_test[DeepSeek-R1_tp8-stress_time_3600s_timeout_5400s-MAX_UTILIZATION-pytorch-stress-test-with-accuracy]
disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-deepseek_r1_v2_fp4_stress]
disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-gpt_oss_120b_stress]
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1LongBenchV2::test_fp8_8gpus
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1LongBenchV2::test_nvfp4_4gpus