[Misc] Revert compressed-tensors code reuse (#7521)

This commit is contained in:
Kyle Sayers
2024-08-14 15:07:37 -07:00
committed by GitHub
parent 951fdd66d3
commit f55a9aea45
8 changed files with 85 additions and 13 deletions
@@ -5,12 +5,13 @@ 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", [