From 758cc4f9e1aa0ff2efa65a33343c76545b1b0540 Mon Sep 17 00:00:00 2001
From: MOVZX <movzx@yahoo.com>
Date: Sat, 26 Sep 2026 20:48:08 +0000
Subject: [PATCH] [Qwen3.5] Pass quant_config and prefix to embed_tokens in
 Qwen3_5Model

Apply the qwen3_5_quantized_embedding patch: construct the embedding
through the model's quant config so quantized (e.g. fp8/int8)
embeddings are supported, and give it a stable prefix for weight
loading.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
---
 vllm/model_executor/models/qwen3_5.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/vllm/model_executor/models/qwen3_5.py b/vllm/model_executor/models/qwen3_5.py
index ac27296461..124d3bbbec 100644
--- a/vllm/model_executor/models/qwen3_5.py
+++ b/vllm/model_executor/models/qwen3_5.py
@@ -247,6 +247,8 @@ class Qwen3_5Model(Qwen3NextModel):
         self.embed_tokens = VocabParallelEmbedding(
             self.vocab_size,
             config.hidden_size,
+            quant_config=self.quant_config,
+            prefix=f"{prefix}.embed_tokens",
         )
 
         def get_layer(prefix: str):