text-generation-inference/backends/vllm
2025-01-30 16:12:52 +01:00
..
src backend(vllm): map ResultOutput to InferStreamResponse to stream back to the client 2025-01-30 16:12:52 +01:00
Cargo.toml backend(vllm): expose FFI for CompletionOutput and RequestOutput on Rust side 2025-01-30 13:35:21 +01:00