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

[CORE] Adding support for insertion of soft-tuned prompts (#4645)

Browse Source 
Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
This commit is contained in:
Swapnil Parekh
2024-07-09 16:26:36 -04:00
committed by GitHub
parent a0550cbc80
commit 4d6ada947c
48 changed files with 1952 additions and 519 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/entrypoints/openai/api_server.py
View File

@@ -116,7 +116,7 @@ async def detokenize(request: DetokenizeRequest):
@app.get("/v1/models")
async def show_available_models():
models = await openai_serving_chat.show_available_models()
models = await openai_serving_completion.show_available_models()
return JSONResponse(content=models.model_dump())
@@ -236,7 +236,8 @@ if __name__ == "__main__":
args.lora_modules,
args.chat_template)
openai_serving_completion = OpenAIServingCompletion(
engine, model_config, served_model_names, args.lora_modules)
engine, model_config, served_model_names, args.lora_modules,
args.prompt_adapters)
openai_serving_embedding = OpenAIServingEmbedding(engine, model_config,
served_model_names)
app.root_path = args.root_path