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][infra] Skip test_eagle3 test with device memory check (#6617)

Browse Source 
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
This commit is contained in:
Leslie Fang 2025-08-05 14:36:03 +08:00 committed by GitHub
parent 7625845365
commit 164acfa31e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 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

@ -1955,6 +1955,7 @@ class TestQwen3_8B(LlmapiAccuracyTestHarness):
task = MMLU(self.MODEL_NAME)
task.evaluate(llm)
@pytest.mark.skip_less_device_memory(140000) ## OOM on 80G H100
@parametrize_with_ids("eagle3_one_model", [True, False])
@parametrize_with_ids("enable_chunked_prefill", [False, True])
def test_eagle3(self, enable_chunked_prefill, eagle3_one_model):