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). @ 017b42c51788aa67d15f3eb7c2cef3a7ec0dfae7

AlpinDale f9a10145d1 fix: v2 block manager + prefix caching		7 miesięcy temu
..
block	f9a10145d1 fix: v2 block manager + prefix caching	7 miesięcy temu
__init__.py	ac1d46a2ec feat: begin work on the engine	1 rok temu
block_manager_v1.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 miesięcy temu
block_manager_v2.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 miesięcy temu
embedding_model_block_manager.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 miesięcy temu
evictor_v1.py	5fecc6b025 when was this deprecated?	7 miesięcy temu
evictor_v2.py	5fecc6b025 when was this deprecated?	7 miesięcy temu
interfaces.py	237fa59aea feat: support CPU/GPU swapping in BlockManagerV2	7 miesięcy temu
policy.py	fca911ee0a vLLM Upstream Sync (#526)	8 miesięcy temu
scheduler.py	29ddfae8de fix: typo in scheduler	7 miesięcy temu