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). @ premature-exit-async

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