text-generation-inference/backends/vllm/src
2025-01-31 10:56:54 +01:00
..
backend.rs backend(vllm): disable metrics for now 2025-01-31 10:56:54 +01:00
engine.rs backend(vllm): map ResultOutput to InferStreamResponse to stream back to the client 2025-01-30 16:12:52 +01:00
errors.rs backend(vllm): submit new request to vLLM engine 2025-01-27 22:39:35 +01:00
lib.rs backend(vllm): disable metrics for now 2025-01-31 10:56:54 +01:00
main.rs backend(vllm): submit new request to vLLM engine 2025-01-27 22:39:35 +01:00