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). @ d91e4e98e1c3cb21340e435bb28f643613d9d5a7

AlpinDale 22a4cd4595 core: fix spec decode metrics and envs circular import (#889)		пре 1 месец
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	пре 8 месеци
abstract.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
blocksparse_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
flash_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
flashinfer.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
ipex_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
openvino.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
pallas.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
placeholder_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
rocm_flash_attn.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	пре 1 месец
torch_sdpa.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
utils.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец
xformers.py	1405051912 attention: add `AttentionState` abstraction (#863)	пре 1 месец