biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Quantization] Bump compressed-tensors version; update NVFP4A16 test model (#19224)

Browse Source 
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
This commit is contained in:
Dipika Sikka
2025-06-06 04:21:54 -04:00
committed by GitHub
parent 0d49483ea9
commit 94870359cd
3 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/quantization/test_compressed_tensors.py
View File

@@ -651,10 +651,9 @@ def test_compressed_tensors_2of4_sparse_compressed(vllm_runner, args_2of4):
assert output
@pytest.mark.skip(reason="Skip until the model config is updated")
def test_compressed_tensors_nvfp4a16(vllm_runner):
# run weight only example
model = "nm-testing/TinyLlama-1.1B-Chat-v1.0-FP4"
model = "nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4A16"
with vllm_runner(model, enforce_eager=True) as llm:
def check_model(model):