[2/3] fix dsv3 awq issue (#4625)

Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: laixinn <xielx@shanghaitech.edu.cn>
This commit is contained in:
AniZpZ
2025-04-04 08:36:39 +08:00
committed by GitHub
parent e53bf190bc
commit d95269f9b3
8 changed files with 1139 additions and 42 deletions

View File

@@ -61,6 +61,7 @@ from sglang.srt.layers.quantization.compressed_tensors.compressed_tensors import
from sglang.srt.layers.quantization.fp8 import Fp8Config
from sglang.srt.layers.quantization.gptq import GPTQConfig, GPTQMarlinConfig
from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp8Config
from sglang.srt.layers.quantization.moe_wna16 import MoeWNA16Config
from sglang.srt.layers.quantization.w8a8_fp8 import W8A8Fp8Config
from sglang.srt.layers.quantization.w8a8_int8 import W8A8Int8Config
from sglang.srt.layers.vocab_parallel_embedding import (
@@ -75,6 +76,7 @@ BASE_QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"modelopt": ModelOptFp8Config,
"w8a8_int8": W8A8Int8Config,
"w8a8_fp8": W8A8Fp8Config,
"moe_wna16": MoeWNA16Config,
"compressed-tensors": CompressedTensorsConfig,
}