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). @ feat/jamba-support

AlpinDale fe17712f29 fully working chunked prefill		9 mesiacov pred
..
block	df7ae8ce01 fix spec_decode and block imports	9 mesiacov pred
__init__.py	ac1d46a2ec feat: begin work on the engine	1 rok pred
block_manager_v1.py	f52aa64fe6 use the get_len() method instead of manual len calculation	9 mesiacov pred
block_manager_v2.py	fa083286e3 Speculative Decoding Part 4: Lookahead scheduling (#402)	9 mesiacov pred
evictor.py	375f24ccca fix: optimize context shift performance (#380)	9 mesiacov pred
interfaces.py	fa083286e3 Speculative Decoding Part 4: Lookahead scheduling (#402)	9 mesiacov pred
policy.py	6f00203041 refactor scheduler for chunked prefill, remove reorder policy for now	9 mesiacov pred
scheduler.py	fe17712f29 fully working chunked prefill	9 mesiacov pred