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). @ dry-seq-breakers-pad

AlpinDale 1405051912 attention: add `AttentionState` abstraction (#863)		1 ヶ月前
..
backends	1405051912 attention: add `AttentionState` abstraction (#863)	1 ヶ月前
ops	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 ヶ月前
__init__.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 ヶ月前
layer.py	bf88c8567e feat: mamba model support (#674)	4 ヶ月前
selector.py	5d37ec1016 suppress tpu import warning (#696)	4 ヶ月前