From dd04a96ee3caa8c85fbc72a6328b969d1c373bc9 Mon Sep 17 00:00:00 2001 From: weiguihua2 Date: Fri, 22 Aug 2025 17:08:56 +0800 Subject: [PATCH] [Bugfix] Fix the bug of incorrect precision (#2479) ### What this PR does / why we need it? Fix the bug of incorrect precision - vLLM version: v0.10.0 - vLLM main: https://github.com/vllm-project/vllm/commit/53415653ff24be03e7c90f5b42ef9cb3f72aad71 --------- Signed-off-by: weiguihua2 --- vllm_ascend/quantization/quantizer.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/vllm_ascend/quantization/quantizer.py b/vllm_ascend/quantization/quantizer.py index 487597c..988f8bd 100644 --- a/vllm_ascend/quantization/quantizer.py +++ b/vllm_ascend/quantization/quantizer.py @@ -75,8 +75,8 @@ class VLLMAscendQuantizer: "vllm.model_executor.layers.layernorm.RMSNorm", "__init__", [wrapper_rmsnorm_init]) VLLMAscendQuantizer.apply_patch( - "vllm.model_executor.layers.layernorm.RMSNorm", - "forward_oot", [wrapper_rmsnorm_forward_oot]) + "vllm_ascend.ops.layernorm.AscendRMSNorm", "forward_oot", + [wrapper_rmsnorm_forward_oot]) VLLMAscendQuantizer.apply_patch( "vllm.model_executor.layers.vocab_parallel_embedding.VocabParallelEmbedding", "__init__", [wrapper_vocab_parallel_embedding_init])