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). @ feat/jamba-support

AlpinDale 083ba7b452 roll back chunked prefill changes to SDPA, isolate cpu worker		9 maanden geleden
..
__init__.py	0f1399c135 feat: attention refactor part 2	10 maanden geleden
abstract.py	fe17712f29 fully working chunked prefill	9 maanden geleden
flash_attn.py	fe17712f29 fully working chunked prefill	9 maanden geleden
rocm_flash_attn.py	fe17712f29 fully working chunked prefill	9 maanden geleden
sdpa.py	083ba7b452 roll back chunked prefill changes to SDPA, isolate cpu worker	9 maanden geleden
xformers.py	fe17712f29 fully working chunked prefill	9 maanden geleden