EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Bugfix] fix bug about model type of qwen3_vl_8b_instruct_w8a8 (#7383)

Browse Source 
### What this PR does / why we need it?
Adapt to the model type of Qwen3-VL-8B-Instruct-W8A8

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
This commit is contained in:
jiangmengyu18
2026-03-18 20:30:03 +08:00
committed by GitHub
parent fb8e22ec00
commit 305820f1a9
4 changed files with 15 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/quantization/modelslim_config.py
View File

@@ -57,7 +57,7 @@ QUANT_MODEL_PREFIX_MAPPINGS: dict[str, dict[str, str]] = {
"language_model.lm_head.": "lm_head.",
"language_model.model.": "model.language_model.",
},
"qwen3_vl_text": {
"qwen3_vl": {
"visual.": "model.visual.",
"language_model.lm_head.": "lm_head.",
"language_model.model.": "model.language_model.",