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). @ 7581d43909a894ba2da7c5c88d09eb1cee4661c8

AlpinDale 1405051912 attention: add `AttentionState` abstraction (#863)		1 kuukausi sitten
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 kuukautta sitten
abstract.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
blocksparse_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
flash_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
flashinfer.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
ipex_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
openvino.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
pallas.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
placeholder_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
rocm_flash_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
torch_sdpa.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
utils.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten
xformers.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 kuukausi sitten