[BugFix] fix 3vl dense model load quant weight (#6100)

### What this PR does / why we need it?
Fix Qwen3VL dense quant model load weights Error. 

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
The Qwen3VL quantized model service initialized successfully. Inference
requests are processed correctly, and valid responses are returned.

- vLLM version: v0.13.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/d68209402ddab3f54a09bc1f4de9a9495a283b60

Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
This commit is contained in:
shaopeng-666 authored and GitHub committed 2026-01-22 20:05:25 +08:00
1 parent 7f91ac2649
commit 176bfc36bc
1 file changed
+5
+5
View File
@@ -210,6 +210,11 @@ QUANT_MODEL_PREFIX_MAPPINGS = {
"language_model.lm_head.": "lm_head.",
"language_model.model.": "model.language_model.",
},
"qwen3_vl_text": {
"visual.": "model.visual.",
"language_model.lm_head.": "lm_head.",
"language_model.model.": "model.language_model.",
},
}
packed_modules_model_mapping = {