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

[Nvbug/5383670] fix: switch test case to non-fp4 ckpt for more GPU coverage (#5882)

Browse Source 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
This commit is contained in:
Kaiyu Xie 2025-07-14 19:21:46 +08:00 committed by GitHub
parent c720d7f779
commit aa97fbb2ad
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/unittest/llmapi/test_llm.py
View File

@ -544,8 +544,7 @@ def _test_llm_generate_async(model_name=default_model_name,
@pytest.mark.parametrize("chunked", [True, False])
@pytest.mark.part0
def test_llm_generate_async_with_stream_interval(chunked):
pytest.skip("https://nvbugs/5383670")
model_path = f"{llm_models_root()}/nvfp4-quantized/Meta-Llama-3.1-8B"
model_path = get_model_path('llama-models-v2/llama-v2-7b-hf')
max_num_tokens = 256
with LLM_torch(model_path,
max_num_tokens=max_num_tokens,