vllm open ai api
#1
by
prudant
- opened
hi, can be served by open ai vllm api? if yes can you give us an usage example with open ai api client over vllm?
nice jobs
regards!
Same question here!
You apparently need to add this flag to vllm serve --hf_overrides '{"architectures": ["Qwen3ForSequenceClassification"],"classifier_from_token": ["no", "yes"],"is_original_qwen3_reranker": true}'