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

[Misc] compressed-tensors code reuse (#7277)

Browse Source
This commit is contained in:
Kyle Sayers
2024-08-13 19:05:15 -04:00
committed by GitHub
parent 33e5d7e6b6
commit 373538f973
8 changed files with 13 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/quantization/test_compressed_tensors.py
View File

@@ -5,13 +5,12 @@ Run `pytest tests/quantization/test_compressed_tensors.py`.
import pytest
import torch
from compressed_tensors.quantization import QuantizationType
from vllm.model_executor.layers.quantization.compressed_tensors.compressed_tensors import ( # noqa: E501
CompressedTensorsLinearMethod, CompressedTensorsW4A16Sparse24,
CompressedTensorsW8A8Fp8, CompressedTensorsW8A8Int8,
CompressedTensorsW8A16Fp8, CompressedTensorsWNA16)
from vllm.model_executor.layers.quantization.compressed_tensors.utils import (
QuantizationType)
@pytest.mark.parametrize("model_args", [