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][ci] Waive qwen3 test for accuracy bug in https://nvbugs/5505402 (#7585)

Browse Source 
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit is contained in:
dominicshanshan 2025-09-06 21:29:16 +08:00 committed by GitHub
parent caf9b9cd42
commit 9a97f0a3b7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 0 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

@ -2317,6 +2317,7 @@ class TestQwen3_8B(LlmapiAccuracyTestHarness):
MODEL_NAME = "Qwen3/Qwen3-8B"
@skip_pre_hopper
@pytest.mark.skip(reason="https://nvbugs/5505402")
@pytest.mark.parametrize(
"tp_size,pp_size,ep_size,attention_dp,cuda_graph,overlap_scheduler",
[(1, 1, 1, False, True, True)],

1
tests/integration/test_lists/test-db/l0_b200.yml
View File

@ -37,6 +37,7 @@ l0_b200:
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
- accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency] # nvbugs 5505402
- disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]