NumKong: 2'000 Mixed Precision Kernels for All
ashvardanian
39 points
2 comments
March 20, 2026
Related Discussions
Found 5 related stories in 52.5ms across 3,471 title embeddings via pgvector HNSW
- NanoGPT Slowrun: 10x Data Efficiency with Infinite Compute sdpmas · 122 pts · March 19, 2026 · 45% similar
- TurboQuant: Building a Sub-Byte KV Cache Quantizer from Paper to Production wizzense · 13 pts · March 27, 2026 · 45% similar
- AutoKernel: Autoresearch for GPU Kernels frozenseven · 44 pts · March 11, 2026 · 44% similar
- Show HN: GDSL – 800 line kernel: Lisp subset in 500, C subset in 1300 FirTheMouse · 62 pts · March 15, 2026 · 42% similar
- TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS aegis_camera · 76 pts · April 01, 2026 · 42% similar
Discussion Highlights (1 comments)
jmalicki
I wish this had a README.md written by a human so I could understand what the project was about, since it sounds cool on the surface.