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