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). @ chore/test-updates

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