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). @ deepseek_v3

AlpinDale 1390915778 multi-step: add support for flashinfer attention backend (#1033)		2 hete
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
abstract.py	1390915778 multi-step: add support for flashinfer attention backend (#1033)	2 hete
blocksparse_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 hónapja
flash_attn.py	1390915778 multi-step: add support for flashinfer attention backend (#1033)	2 hete
flashinfer.py	1390915778 multi-step: add support for flashinfer attention backend (#1033)	2 hete
ipex_attn.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 hónapja
openvino.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 hónapja
pallas.py	032974a28a tpu: fix TPU type api (#975)	2 hete
placeholder_attn.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 hete
rocm_flash_attn.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 hete
torch_sdpa.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 hónapja
utils.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	2 hete
xformers.py	1405051912 attention: add `AttentionState` abstraction (#863)	1 hónapja