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). @ quip-return

AlpinDale 22a4cd4595 core: fix spec decode metrics and envs circular import (#889)		3 weeks ago
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 months ago
abstract.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
blocksparse_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
flash_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
flashinfer.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
ipex_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
openvino.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
pallas.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
placeholder_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
rocm_flash_attn.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 weeks ago
torch_sdpa.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
utils.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago
xformers.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 month ago