NumKong: 2'000 Mixed Precision Kernels for All
ashvardanian
39 points
2 comments
March 20, 2026
Related Discussions
Found 5 related stories in 802.6ms across 14,015 title embeddings via pgvector HNSW
- KVarN: Native vLLM backend for KV-cache quantization by Huawei theanonymousone · 127 pts · June 04, 2026 · 52% similar
- 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
- Kore: Binary File Format Optimized for Modern Data Systems (Open Source) arunkore2026 · 11 pts · May 30, 2026 · 45% similar
- MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU chrsw · 280 pts · April 08, 2026 · 44% 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.