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). @ b753ff7870b5787d9e34cb56b717f51aa6b830e6

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