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). @ ed6717d0c064a1cbf0fe9f358008ffc43e20187a

AlpinDale ed6717d0c0 feat: initial support for control vectors		5 kuukautta sitten
..
block	6ac658b0d6 some small performance improvements	5 kuukautta sitten
__init__.py	ac1d46a2ec feat: begin work on the engine	1 vuosi sitten
block_manager_v1.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	5 kuukautta sitten
block_manager_v2.py	ae04f57ec1 feat: Pipeline Parallel support (#581)	5 kuukautta sitten
embedding_model_block_manager.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	6 kuukautta sitten
evictor_v1.py	5fecc6b025 when was this deprecated?	6 kuukautta sitten
evictor_v2.py	5fecc6b025 when was this deprecated?	6 kuukautta sitten
interfaces.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	6 kuukautta sitten
policy.py	fca911ee0a vLLM Upstream Sync (#526)	7 kuukautta sitten
scheduler.py	ed6717d0c0 feat: initial support for control vectors	5 kuukautta sitten