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

[MODEL] Qwen Multimodal Support (Qwen-VL / Qwen-VL-Chat) (#8029)

Browse Source 
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Alex Brooks
2024-09-05 06:48:10 -06:00
committed by GitHub
parent 8685ba1a1e
commit 9da25a88aa
8 changed files with 1111 additions and 209 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -51,7 +51,6 @@ _GENERATION_MODELS = {
"PhiForCausalLM": ("phi", "PhiForCausalLM"),
"Phi3ForCausalLM": ("llama", "LlamaForCausalLM"),
"PhiMoEForCausalLM": ("phimoe", "PhiMoEForCausalLM"),
"QWenLMHeadModel": ("qwen", "QWenLMHeadModel"),
"Qwen2ForCausalLM": ("qwen2", "Qwen2ForCausalLM"),
"Qwen2MoeForCausalLM": ("qwen2_moe", "Qwen2MoeForCausalLM"),
"RWForCausalLM": ("falcon", "FalconForCausalLM"),
@@ -88,6 +87,7 @@ _MULTIMODAL_MODELS = {
"PaliGemmaForConditionalGeneration"),
"Phi3VForCausalLM": ("phi3v", "Phi3VForCausalLM"),
"UltravoxModel": ("ultravox", "UltravoxModel"),
"QWenLMHeadModel": ("qwen", "QWenLMHeadModel"),
}
_CONDITIONAL_GENERATION_MODELS = {
"BartModel": ("bart", "BartForConditionalGeneration"),