gpu-kernels

Open repos and models their makers tagged gpu-kernels, most starred first. The same for everyone.

AI on my own machineRepo

MacSeek

From-scratch Metal inference engine that runs DeepSeek-V4.1-Flash (233 GB GGUF) with 200K context on a 64 GB Mac — 7x faster prefill, 12x faster decode than llama.cpp. OpenAI-compatible server + web UI.

  • 1
  • C++
  • MIT
  • 2 wk ago
arnavprabhuTake it
Search GitHub and Hugging Face for gpu-kernels

Get , open it once and sign in. Then come back here and press the button again.