chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[3/3] fix dsv3 awq issue (#4719)

Browse Source 
Co-authored-by: AniZpZ <aniz1905@gmail.com>
This commit is contained in:
laixin
2025-03-27 14:13:43 +08:00
committed by GitHub
parent 1099f6c974
commit ae25d36dc6
2 changed files with 204 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
python/sglang/srt/layers/quantization/__init__.py
View File

@@ -9,7 +9,6 @@ import torch
try:
from vllm.model_executor.layers.quantization.aqlm import AQLMConfig
from vllm.model_executor.layers.quantization.awq import AWQConfig
from vllm.model_executor.layers.quantization.awq_marlin import AWQMarlinConfig
from vllm.model_executor.layers.quantization.bitsandbytes import BitsAndBytesConfig
from vllm.model_executor.layers.quantization.deepspeedfp import DeepSpeedFPConfig
@@ -33,14 +32,15 @@ except ImportError:
class DummyConfig:
pass
AQLMConfig = AWQConfig = AWQMarlinConfig = BitsAndBytesConfig = (
CompressedTensorsConfig
) = DummyConfig
AQLMConfig = AWQMarlinConfig = BitsAndBytesConfig = CompressedTensorsConfig = (
DummyConfig
)
DeepSpeedFPConfig = ExpertsInt8Config = FBGEMMFp8Config = GGUFConfig = (
GPTQMarlin24Config
) = DummyConfig
MarlinConfig = QQQConfig = Int8TpuConfig = DummyConfig
from sglang.srt.layers.quantization.awq import AWQConfig
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.quantization.blockwise_int8 import BlockInt8Config
from sglang.srt.layers.quantization.compressed_tensors.compressed_tensors import (