david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ feat/function-calling

AlpinDale c0aac15421 feat: S-LoRA support (#222)		před 1 rokem
..
__init__.py	ac1d46a2ec feat: begin work on the engine	před 1 rokem
block_manager.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	před 1 rokem
policy.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	před 1 rokem
scheduler.py	c0aac15421 feat: S-LoRA support (#222)	před 1 rokem