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

Remove references to squeezellm (#1603)

Browse Source
This commit is contained in:
Jani Monoses
2024-10-07 21:30:41 +03:00
committed by GitHub
parent 2b302b9393
commit 3ff641132e
2 changed files with 0 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -19,7 +19,6 @@ from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinConfig
from vllm.model_executor.layers.quantization.gptq_marlin_24 import GPTQMarlin24Config
from vllm.model_executor.layers.quantization.marlin import MarlinConfig
from vllm.model_executor.layers.quantization.qqq import QQQConfig
from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
from sglang.srt.layers.quantization.base_config import QuantizationConfig
@@ -39,7 +38,6 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"gptq_marlin": GPTQMarlinConfig,
"awq_marlin": AWQMarlinConfig,
"gptq": GPTQConfig,
"squeezellm": SqueezeLLMConfig,
"compressed-tensors": CompressedTensorsConfig,
"bitsandbytes": BitsAndBytesConfig,
"qqq": QQQConfig,

1
python/sglang/srt/server_args.py
View File

@@ -266,7 +266,6 @@ class ServerArgs:
"marlin",
"gptq_marlin",
"awq_marlin",
"squeezellm",
"bitsandbytes",
],
help="The quantization method.",