chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[QuickFix] fix gptq model initialize (#6429)

Browse Source
This commit is contained in:
PGFLMG
2025-05-20 12:17:10 +08:00
committed by GitHub
parent 6317c5c61f
commit 83f2d9d4ed
2 changed files with 303 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
python/sglang/srt/layers/quantization/__init__.py
View File

@@ -25,7 +25,6 @@ try:
from vllm.model_executor.layers.quantization.gptq import GPTQLinearMethod
from vllm.model_executor.layers.quantization.gptq_marlin import (
GPTQMarlinLinearMethod,
GPTQMarlinMoEMethod,
)
from vllm.model_executor.layers.quantization.gptq_marlin_24 import (
GPTQMarlin24Config,
@@ -58,7 +57,11 @@ from sglang.srt.layers.quantization.compressed_tensors.compressed_tensors import
CompressedTensorsConfig,
)
from sglang.srt.layers.quantization.fp8 import Fp8Config
from sglang.srt.layers.quantization.gptq import GPTQConfig, GPTQMarlinConfig
from sglang.srt.layers.quantization.gptq import (
GPTQConfig,
GPTQMarlinConfig,
GPTQMarlinMoEMethod,
)
from sglang.srt.layers.quantization.modelopt_quant import (
ModelOptFp4Config,
ModelOptFp8Config,