Skip to content

GitLab

"ssh:/git@developer.sourcefind.cn:2222/OpenDAS/vllm_cscc.git" did not exist on "ad517f954382ef4e207ab4a6fd9aa12cbe7a389f"
Unverified Commit 493c2753 authored by Vensen's avatar Vensen Committed by GitHub
Browse files

Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor (#19643) 


Signed-off-by: default avatarVensenmu <vensenmu@gmail.com>
parent f39ab2d4
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/model_executor/models/gemma3_mm.py
View file @ 493c2753
...@@ -479,6 +479,7 @@ class Gemma3ForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsPP, ...@@ -479,6 +479,7 @@ class Gemma3ForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsPP,
"model.vision_tower.": "vision_tower.", "model.vision_tower.": "vision_tower.",
"model.multi_modal_projector.": "multi_modal_projector.", "model.multi_modal_projector.": "multi_modal_projector.",
"lm_head.": "language_model.lm_head.", "lm_head.": "language_model.lm_head.",
"vision_tower.vision_model.": "vision_model.",
}) })
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""): def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment