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

[Bugfix] Fix Phi3.5 mini and MoE LoRA inference (#8571)

Browse Source
This commit is contained in:
Amit Garg
2024-09-19 17:54:02 -07:00
committed by GitHub
parent de6f90a13d
commit 18ae428a0d
3 changed files with 22 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -50,7 +50,7 @@ _GENERATION_MODELS = {
"OrionForCausalLM": ("orion", "OrionForCausalLM"),
"PersimmonForCausalLM": ("persimmon", "PersimmonForCausalLM"),
"PhiForCausalLM": ("phi", "PhiForCausalLM"),
"Phi3ForCausalLM": ("llama", "LlamaForCausalLM"),
"Phi3ForCausalLM": ("phi3", "Phi3ForCausalLM"),
"PhiMoEForCausalLM": ("phimoe", "PhiMoEForCausalLM"),
"Qwen2ForCausalLM": ("qwen2", "Qwen2ForCausalLM"),
"Qwen2MoeForCausalLM": ("qwen2_moe", "Qwen2MoeForCausalLM"),