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). @ feat/perplexity

AlpinDale 16615784b3 fix: prefix cache for turing gpus		преди 11 месеца
..
__init__.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	преди 1 година
fused_moe.py	7d6ba53602 feat: fused top-k kernels for MoE (#273)	преди 11 месеца
prefix_prefill.py	16615784b3 fix: prefix cache for turing gpus	преди 11 месеца