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). @ cuda_lora

AlpinDale 7a313483f1 chore: move update_flash_attn_metadata to attn backend (#731)		4 mēneši atpakaļ
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mēneši atpakaļ
abstract.py	7a313483f1 chore: move update_flash_attn_metadata to attn backend (#731)	4 mēneši atpakaļ
blocksparse_attn.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mēneši atpakaļ
flash_attn.py	7a313483f1 chore: move update_flash_attn_metadata to attn backend (#731)	4 mēneši atpakaļ
flashinfer.py	60b702a827 chore: register custom torch ops for flash-attn and flashinfer (#724)	4 mēneši atpakaļ
ipex_attn.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mēneši atpakaļ
openvino.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mēneši atpakaļ
pallas.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mēneši atpakaļ
placeholder_attn.py	bf88c8567e feat: mamba model support (#674)	4 mēneši atpakaļ
rocm_flash_attn.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 mēneši atpakaļ
torch_sdpa.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mēneši atpakaļ
utils.py	3bbb3f2086 feat: add numpy implementation of `compute_slot_mapping` (#678)	4 mēneši atpakaļ
xformers.py	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	4 mēneši atpakaļ