Remove references to squeezellm (#1603)

sgl-project · Oct 7, 2024 · 3ff6411 · 3ff6411
1 parent 2b302b9
commit 3ff6411
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 3 deletions.
diff --git a/python/sglang/srt/layers/quantization/__init__.py b/python/sglang/srt/layers/quantization/__init__.py
@@ -19,7 +19,6 @@
 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 @@
     "gptq_marlin": GPTQMarlinConfig,
     "awq_marlin": AWQMarlinConfig,
     "gptq": GPTQConfig,
-    "squeezellm": SqueezeLLMConfig,
     "compressed-tensors": CompressedTensorsConfig,
     "bitsandbytes": BitsAndBytesConfig,
     "qqq": QQQConfig,

diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
@@ -266,7 +266,6 @@ def add_cli_args(parser: argparse.ArgumentParser):
                 "marlin",
                 "gptq_marlin",
                 "awq_marlin",
-                "squeezellm",
                 "bitsandbytes",
             ],
             help="The quantization method.",