youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[CI Failure] Fix torchao dep failure for Quantization Test (#26824)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-10-14 19:41:43 -04:00
committed by GitHub
parent 4aed506b65
commit 7e0ef4084a
4 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/quantization/test_compressed_tensors.py
View File

@ -697,7 +697,8 @@ def test_compressed_tensors_2of4_sparse_compressed(vllm_runner, args_2of4):
@pytest.mark.parametrize(
"args",
[
("nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4A16", CompressedTensorsW4A16Fp4),
# TODO: Enable once model is available again
# ("nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4A16", CompressedTensorsW4A16Fp4),
("nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4", CompressedTensorsW4A4Fp4),
],
)