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). @ windows_support

şunun yansıması https://github.com/PygmalionAI/aphrodite-engine

AlpinDale 064c701d18 formatting		4 ay önce
..
dequantize.cuh	9f7a0e3ecb feat: AWQ support for Turing GPUs (#53)	1 yıl önce
gemm_kernels.cu	064c701d18 formatting	4 ay önce