From 7c876de7f5930583797f5df44e4f4028285431e1 Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Sat, 20 Sep 2025 01:47:01 -0700 Subject: [PATCH] fix: remove awq_dequantize deps (#10686) --- python/sglang/srt/models/deepseek_v2.py | 2 +- python/sglang/srt/models/longcat_flash.py | 2 +- python/sglang/srt/models/longcat_flash_nextn.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/python/sglang/srt/models/deepseek_v2.py b/python/sglang/srt/models/deepseek_v2.py index df2a89029..151b9e66e 100644 --- a/python/sglang/srt/models/deepseek_v2.py +++ b/python/sglang/srt/models/deepseek_v2.py @@ -164,7 +164,7 @@ elif _is_hip: awq_dequantize_triton as awq_dequantize, ) else: - from vllm._custom_ops import awq_dequantize + pass if _is_hip: from sglang.srt.layers.attention.triton_ops.rocm_mla_decode_rope import ( diff --git a/python/sglang/srt/models/longcat_flash.py b/python/sglang/srt/models/longcat_flash.py index 3fdd8f643..8af280771 100644 --- a/python/sglang/srt/models/longcat_flash.py +++ b/python/sglang/srt/models/longcat_flash.py @@ -131,7 +131,7 @@ elif _is_hip: awq_dequantize_triton as awq_dequantize, ) else: - from vllm._custom_ops import awq_dequantize + pass logger = logging.getLogger(__name__) diff --git a/python/sglang/srt/models/longcat_flash_nextn.py b/python/sglang/srt/models/longcat_flash_nextn.py index 64a4265c5..69bd1548d 100644 --- a/python/sglang/srt/models/longcat_flash_nextn.py +++ b/python/sglang/srt/models/longcat_flash_nextn.py @@ -111,7 +111,7 @@ elif _is_hip: awq_dequantize_triton as awq_dequantize, ) else: - from vllm._custom_ops import awq_dequantize + pass logger = logging.getLogger(__name__)