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). @ sampling-kernels

AlpinDale 6ac658b0d6 some small performance improvements		vor 5 Monaten
..
block	6ac658b0d6 some small performance improvements	vor 5 Monaten
__init__.py	ac1d46a2ec feat: begin work on the engine	vor 1 Jahr
block_manager_v1.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	vor 5 Monaten
block_manager_v2.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	vor 5 Monaten
embedding_model_block_manager.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	vor 5 Monaten
evictor_v1.py	5fecc6b025 when was this deprecated?	vor 5 Monaten
evictor_v2.py	5fecc6b025 when was this deprecated?	vor 5 Monaten
interfaces.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	vor 5 Monaten
policy.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
scheduler.py	e76bbe72eb chore: handle aborted requests for jamba	vor 5 Monaten