gpu-kernels
gpu-kernel-runner
Runs a single CUDA/OpenCL kernel, taking its source from a file and arguments from the command-line
- 27
- C++
- BSD-3-Clause
- 2 d ago
quadbit
The only deployed sparse FP4 GEMM on SM120: beats CUTLASS 80b on every shape, wins end-to-end request latency in 81 of 112 serving regimes vs dense NVFP4.
- 3
- Python
- MIT
- 2 wk ago
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
Litmus
Error bounds and targeted falsification for Triton kernels
Runs in the browser on Hugging Face
- 0
- apache-2.0
- 3 mo ago
