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). @ d49ead733470fdfcd74eed957bba9fb50258d5e7

AlpinDale 22a4cd4595 core: fix spec decode metrics and envs circular import (#889)		1 bulan lalu
..
configs	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 bulan lalu
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 bulan lalu
fused_moe.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	1 bulan lalu
layer.py	d34e083c48 feat: add experts_int8 support (#730)	4 bulan lalu
moe_pallas.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 bulan lalu