1.JMS1717 / ming-voiceLow-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linuxamdlocal-llmradeonrealtimerocmspeech-to-speech+3 morePythonMIT423 total25 forks+133 starsfrom 285 · score 4.90
2.LMCache / LMCacheLMCache: Supercharge Your LLM with the Fastest KV Cache Layeramdcudainferencekv-cachellmpytorch+4 morePythonAPACHE-2.012K total2.1K forks+92 starsfrom 12,164 · score 4.53
3.Motphys / Uni-SuperMimicSuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.amdmotrixsimmujocorocmunilabmjwarp+4 morePythonAPACHE-2.0231 total19 forks+90 starsfrom 128 · score 4.51
4.apache / tvmOpen Machine Learning Compiler Frameworkcompilertensordeep-learninggpuopenclmetal+7 morePythonAPACHE-2.014K total4K forks+24 starsfrom 13,862 · score 3.22
5.cupy / cupyNumPy & SciPy for GPUcudacudnncublascusolverncclpython+12 morePythonMIT12K total1.2K forks+10 starsfrom 12,380 · score 2.40