atoma-network/atoma-infer Issues
feat: embeddings endpoint
Updatedfeat: OpenAPI spec
Updatedfeat: chat completions streaming
UpdatedAdd proper shutdown for `LlmEngine`
Updated 3feat: GET /models
UpdatedAdd features to README
Updated 4Add other backends
UpdatedAdd multi-gpu support
UpdatedLlama integration
Closed 1Code clean-up
UpdatedAdd a Llama inference main file
Closed 4