A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning
Repository Index
47,133 repositories indexed
1–5 of 5 · Most stars
Up to 100x faster strings for C, C++, CUDA, Python, Rust, Swift, JS, & Go, leveraging NEON, AVX2, AVX-512, SVE, GPGPU, & SWAR to accelerate search, hashing, sorting, edit distances, sketches, and memory ops 🦖
Implementations of SIMD instruction sets for systems which don't natively support them.
- simd-intrinsics
- sse
- neon
- arm
Roaring bitmaps in C (and C++), with SIMD (AVX2, AVX-512 and NEON) optimizations: used by Apache Doris, ClickHouse, Alibaba Tair, Redpanda, YDB and StarRocks
- roaring-bitmaps
- visual-studio
- c
- clang
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf