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). @ b01eec7c3554d814b27457439aa9431d554b688d

AlpinDale 935027bdcc feat: dynamic shared memory allocation for moe align block size (#372)		11 hónapja
..
align_block_size_kernel.cu	935027bdcc feat: dynamic shared memory allocation for moe align block size (#372)	11 hónapja
moe_ops.cpp	7d6ba53602 feat: fused top-k kernels for MoE (#273)	1 éve
moe_ops.h	7d6ba53602 feat: fused top-k kernels for MoE (#273)	1 éve
softmax.cu	7d6ba53602 feat: fused top-k kernels for MoE (#273)	1 éve