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

Revert "Integration of TurboMind AWQ" (#2866)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-01-13 04:44:39 -08:00
committed by GitHub
parent f3516c2894
commit 6249e4a19e
8 changed files with 2 additions and 411 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/layers/quantization/__init__.py
View File

@@ -20,7 +20,6 @@ from vllm.model_executor.layers.quantization.marlin import MarlinConfig
from vllm.model_executor.layers.quantization.qqq import QQQConfig
from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
from sglang.srt.layers.quantization.awq_turbomind import AWQTurbomindConfig
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.quantization.fp8 import Fp8Config
from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp8Config
@@ -38,7 +37,6 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"gptq_marlin_24": GPTQMarlin24Config,
"gptq_marlin": GPTQMarlinConfig,
"awq_marlin": AWQMarlinConfig,
"awq_turbomind": AWQTurbomindConfig,
"gptq": GPTQConfig,
"compressed-tensors": CompressedTensorsConfig,
"bitsandbytes": BitsAndBytesConfig,