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). @ chunked_caching_fix

AlpinDale 901900854e chore: consolidate environment variables within one file (#882)		1 месяц назад
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 месяцев назад
abstract.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
blocksparse_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
flash_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
flashinfer.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
ipex_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
openvino.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
pallas.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
placeholder_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
rocm_flash_attn.py	901900854e chore: consolidate environment variables within one file (#882)	1 месяц назад
torch_sdpa.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
utils.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад
xformers.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 месяц назад