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 4d33ce60da feat: Triton flash attention backend for ROCm (#407)		il y a 9 mois
..
__init__.py	df7ae8ce01 fix spec_decode and block imports	il y a 9 mois
batch_expansion.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	il y a 9 mois
interfaces.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	il y a 9 mois
metrics.py	d1786645a3 fix formatting	il y a 9 mois
multi_step_worker.py	2319b411ce refactor: neuron support	il y a 9 mois
spec_decode_worker.py	4d33ce60da feat: Triton flash attention backend for ROCm (#407)	il y a 9 mois
util.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	il y a 9 mois