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

[None][chore] waive failed cases on H100 (#7084)

Browse Source 
Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>
This commit is contained in:
xinhe-nv 2025-08-21 11:15:23 +08:00 committed by GitHub
parent 41ff4901ee
commit 21f4434404
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -1734,6 +1734,7 @@ class TestKimiK2(LlmapiAccuracyTestHarness):
MODEL_PATH = f"{llm_models_root()}/Kimi-K2-Instruct"
@pytest.mark.skip_less_mpi_world_size(8)
@skip_post_blackwell
@skip_pre_hopper
@pytest.mark.parametrize(
"tp_size,pp_size,ep_size,fp8kv,attention_dp,cuda_graph,overlap_scheduler,max_batch_size",

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

@ -631,7 +631,6 @@ test_e2e.py::test_ptp_quickstart_advanced_8gpus_chunked_prefill_sq_22k[Llama-4-S
test_e2e.py::test_relaxed_acceptance_quickstart_advanced_deepseek_r1_8gpus[DeepSeek-R1-DeepSeek-R1/DeepSeek-R1]
test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-image-False]
test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-video-False]
test_e2e.py::test_ptp_quickstart_multimodal[llava-v1.6-mistral-7b-llava-v1.6-mistral-7b-hf-image-False]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image-False]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-video-False]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image-False]

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

@ -164,7 +164,6 @@ test_e2e.py::test_ptp_quickstart_advanced[Llama3.2-11B-BF16-llama-3.2-models/Lla
test_e2e.py::test_ptp_quickstart_advanced[Qwen3-30B-A3B-Qwen3/Qwen3-30B-A3B]
test_e2e.py::test_ptp_quickstart_bert[TRTLLM-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity]
test_e2e.py::test_ptp_quickstart_bert[VANILLA-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity]
test_e2e.py::test_ptp_quickstart_multimodal[llava-v1.6-mistral-7b-llava-v1.6-mistral-7b-hf-image-False]
test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-False]
test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-True]
test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-mixture_text_image-True]

4
tests/integration/test_lists/waives.txt
View File

@ -316,3 +316,7 @@ disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_tp1
examples/test_multimodal.py::test_llm_multimodal_general[Mistral-Small-3.1-24B-Instruct-2503-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5431146)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[latency] SKIP (https://nvbugs/5464461)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5448449)
full:H100/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_eagle3_tp8[eagle3_one_model=True] SKIP (https://nvbugs/5467815)
full:H100/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_eagle3_tp8[eagle3_one_model=False] SKIP (https://nvbugs/5467815)
full:H100/accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8[tp4-cuda_graph=True] SKIP (https://nvbugs/5467815)
full:H100/accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp8_chunked_prefill[tp4ep4-cuda_graph=True] SKIP (https://nvbugs/5467815)