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		vor 8 Monaten
..
attention	1270b5567e triton compile error for flash_attn	vor 8 Monaten
common	6c43e00e60 add jamba modeling code	vor 8 Monaten
distributed	b1caee23a6 cache the p2p access check for memory saving	vor 8 Monaten
endpoints	b1caee23a6 cache the p2p access check for memory saving	vor 8 Monaten
engine	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	vor 8 Monaten
executor	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	vor 8 Monaten
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	vor 10 Monaten
lora	fe17712f29 fully working chunked prefill	vor 8 Monaten
modeling	65cd99ba89 fix KVCache type	vor 8 Monaten
processing	fe17712f29 fully working chunked prefill	vor 8 Monaten
spec_decode	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	vor 8 Monaten
task_handler	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	vor 8 Monaten
transformers_utils	4fbb052b34 add jamba config file	vor 8 Monaten
__init__.py	c2aaaefd57 allow out-of-tree model registry	vor 9 Monaten
py.typed	1c988a48b2 fix logging and add py.typed	vor 1 Jahr