GPU token selection and pipelined decode (1.1.1) - #5

GPU token selection and pipelined decode (1.1.1)#5

jkyberneees merged 1 commit into

mainBackendStack21/mlx-runner:mainfrom

perf/gpu-sampling-pipelined-decodeBackendStack21/mlx-runner:perf/gpu-sampling-pipelined-decodeCopy head branch name to clipboard