Skip to content

Commit 9a97f0a

Browse files
[None][ci] Waive qwen3 test for accuracy bug in https://nvbugs/5505402 (#7585)
Signed-off-by: Wangshanshan <[email protected]>
1 parent caf9b9c commit 9a97f0a

File tree

2 files changed

+2
-0
lines changed

2 files changed

+2
-0
lines changed

tests/integration/defs/accuracy/test_llm_api_pytorch.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2317,6 +2317,7 @@ class TestQwen3_8B(LlmapiAccuracyTestHarness):
23172317
MODEL_NAME = "Qwen3/Qwen3-8B"
23182318

23192319
@skip_pre_hopper
2320+
@pytest.mark.skip(reason="https://nvbugs/5505402")
23202321
@pytest.mark.parametrize(
23212322
"tp_size,pp_size,ep_size,attention_dp,cuda_graph,overlap_scheduler",
23222323
[(1, 1, 1, False, True, True)],

tests/integration/test_lists/test-db/l0_b200.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,7 @@ l0_b200:
3737
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass]
3838
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm]
3939
- accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton]
40+
- accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency] # nvbugs 5505402
4041
- disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551
4142
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
4243
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]

0 commit comments

Comments
 (0)