From 3ff641132e45881ed9ff86be31d673e3ae1d6812 Mon Sep 17 00:00:00 2001
From: Jani Monoses <jani.monoses@gmail.com>
Date: Mon, 7 Oct 2024 21:30:41 +0300
Subject: [PATCH] Remove references to squeezellm (#1603)

---
 python/sglang/srt/layers/quantization/__init__.py | 2 --
 python/sglang/srt/server_args.py                  | 1 -
 2 files changed, 3 deletions(-)

diff --git a/python/sglang/srt/layers/quantization/__init__.py b/python/sglang/srt/layers/quantization/__init__.py
index 5f9619de1..88a05c6d0 100644
--- 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 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,
diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
index e467eb03f..c6e4b2406 100644
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -266,7 +266,6 @@ class ServerArgs:
                 "marlin",
                 "gptq_marlin",
                 "awq_marlin",
-                "squeezellm",
                 "bitsandbytes",
             ],
             help="The quantization method.",