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). @ dcebb8487d766e69cfc28b6712d81e24d90c4691

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