kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-27 14:13:34 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

update cases by comments after reviewed

Browse Source 
Signed-off-by: Jenny Liu <JennyLiu-nv+JennyLiu@users.noreply.github.com>
This commit is contained in:
Jenny Liu 2026-01-12 01:23:25 +00:00
parent 2a581f009d
commit 3a1c58987f
2 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/integration/test_lists/qa/llm_digits_core.txt
View File

@ -32,7 +32,6 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.3-70B-FP4-modelopt-hf-model-hub
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_auto_dtype
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4
accuracy/test_llm_api_pytorch_multimodal.py::TestQwen2_5_VL_7B::test_auto_dtype
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=False]
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[latency_moe_cutlass-torch_compile=True]
accuracy/test_llm_api_pytorch.py::TestPhi4MM::test_fp8

1
tests/integration/test_lists/qa/llm_digits_perf.yml
View File

@ -17,7 +17,6 @@ llm_digits_perf:
- perf/test_perf.py::test_perf[nvidia_nemotron_nano_9b_v2_nvfp4-bench-pytorch-streaming-float4-maxbs:1-input_output_len:2048,128-reqs:1-con:1]
- perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp8-bench-pytorch-streaming-float8-maxbs:1-input_output_len:2048,128-reqs:1-con:1]
- perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp4-bench-pytorch-streaming-float4-maxbs:1-input_output_len:2048,128-reqs:1-con:1]
- perf/test_perf.py::test_perf[llama_v3.1_8b_instruct_fp4-bench-pytorch-streaming-float4-input_output_len:512,128]
- perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-pytorch-streaming-bfloat16-maxbs:1-input_output_len:2048,128-reqs:1-con:1]
- perf/test_perf.py::test_perf[qwen3_8b_fp8-bench-pytorch-streaming-float8-maxbs:1-input_output_len:2048,128-reqs:1-con:1]
- perf/test_perf.py::test_perf[qwen3_8b_fp4-bench-pytorch-streaming-float4-maxbs:1-input_output_len:2048,128-reqs:1-con:1]