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 65cd99ba89 fix KVCache type		9 달 전
..
attention	1270b5567e triton compile error for flash_attn	9 달 전
common	6c43e00e60 add jamba modeling code	9 달 전
distributed	b1caee23a6 cache the p2p access check for memory saving	9 달 전
endpoints	b1caee23a6 cache the p2p access check for memory saving	9 달 전
engine	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	9 달 전
executor	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	9 달 전
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	10 달 전
lora	fe17712f29 fully working chunked prefill	9 달 전
modeling	65cd99ba89 fix KVCache type	9 달 전
processing	fe17712f29 fully working chunked prefill	9 달 전
spec_decode	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	9 달 전
task_handler	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	9 달 전
transformers_utils	4fbb052b34 add jamba config file	9 달 전
__init__.py	c2aaaefd57 allow out-of-tree model registry	9 달 전
py.typed	1c988a48b2 fix logging and add py.typed	1 년 전