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). @ dcb36de9c4faad5b5ff146f13bbf6fb73b228def

AlpinDale 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)		il y a 2 mois
..
__init__.py	5d37ec1016 suppress tpu import warning (#696)	il y a 6 mois
cuda.py	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	il y a 2 mois
interface.py	81c28d2a7f fix: use nvml to get consistent device names (#739)	il y a 5 mois
rocm.py	81c28d2a7f fix: use nvml to get consistent device names (#739)	il y a 5 mois
tpu.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 6 mois