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