biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Add support for the multi-modal Llama 3.2 model (#8811)

Browse Source 
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Chen Zhang
2024-09-25 13:29:32 -07:00
committed by GitHub
parent 4f1ba0844b
commit 770ec6024f
24 changed files with 1646 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/__init__.py
View File

@@ -101,6 +101,8 @@ _MULTIMODAL_MODELS = {
"Qwen2VLForConditionalGeneration": ("qwen2_vl",
"Qwen2VLForConditionalGeneration"),
"UltravoxModel": ("ultravox", "UltravoxModel"),
"MllamaForConditionalGeneration": ("mllama",
"MllamaForConditionalGeneration"),
}
_CONDITIONAL_GENERATION_MODELS = {
"BartModel": ("bart", "BartForConditionalGeneration"),