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). @ rejection_sampling_kernels

AlpinDale 427f6b32fb kernels for rejection sampling		1 månad sedan
..
math.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	2 månader sedan
sampling.cu	427f6b32fb kernels for rejection sampling	1 månad sedan
sampling.cuh	427f6b32fb kernels for rejection sampling	1 månad sedan
utils.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	2 månader sedan
vec_dtypes.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	2 månader sedan