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).

AlpinDale bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)		1 month ago
..
math.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	1 month ago
sampling.cu	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	1 month ago
sampling.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	1 month ago
utils.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	1 month ago
vec_dtypes.cuh	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	1 month ago