EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

fix compressed tensors WNA16 imports (#8142)

Browse Source
This commit is contained in:
Enrique Shockwave
2025-07-18 19:34:14 +01:00
committed by GitHub
parent 719b29f218
commit fd63b62eaa
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
python/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py
View File

@@ -40,7 +40,10 @@ from sglang.srt.layers.quantization.compressed_tensors.utils import (
from sglang.srt.layers.quantization.unquant import UnquantizedLinearMethod from sglang.srt.layers.quantization.unquant import UnquantizedLinearMethod
try: try:
import vllm from vllm.model_executor.layers.quantization.compressed_tensors.schemes.compressed_tensors_wNa16 import (
WNA16_SUPPORTED_BITS,
CompressedTensorsWNA16,
)
VLLM_AVAILABLE = True VLLM_AVAILABLE = True
except ImportError: except ImportError: