owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix vLLM 0.4.1 bug for OpenAI /models route

Browse Source
This commit is contained in:
alpayariyak
2024-06-10 20:38:49 +00:00
parent f19ce12ab0
commit bad5ddd892
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/engine.py
+3
View File
@@ -141,6 +141,9 @@ class OpenAIvLLMEngine:
async def _handle_model_request(self): async def _handle_model_request(self):
models = await self.chat_engine.show_available_models() models = await self.chat_engine.show_available_models()
fixed_model = models.data[0]
fixed_model.id = self.served_model_name
models.data = [fixed_model]
return models.model_dump() return models.model_dump()
async def _handle_chat_or_completion_request(self, openai_request: JobInput): async def _handle_chat_or_completion_request(self, openai_request: JobInput):