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). @ 229733d39fd501ce3a172c6fe48d25cc2c2b2b85

AlpinDale 89c7f0469f fix: calculate the key/value outputs with kvhead		1 год назад
..
__init__.py	ac1d46a2ec feat: begin work on the engine	1 год назад
block_manager.py	89c7f0469f fix: calculate the key/value outputs with kvhead	1 год назад
policy.py	fefbf029c9 revert previous commit	1 год назад
scheduler.py	aad9a61afa chore: formatting and various scheduler fixes	1 год назад