← Back to Discover
artalis-io

artalis-io/bitnet.c

CMITactive
80Health

Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.

Stars19
Forks5
Open Issues1
Contributors5
Last Push3d ago

Health Breakdown

Activity
25
Community
25
Maintenance
15
Popularity
15
#avx2#c#cpu-inference#gguf#inference#kv-cache#llm#moe#neon#quantization#simd#turboquant#wasm
View on GitHub ↗Issues (1) ↗Pull Requests ↗Wiki ↗

Community

artalis-io80

Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.

active
195 contributors3d ago

More C repos

apache
apache/nuttx-apps
Apache NuttX Apps is a collection of tools, shells, network utilities, libraries, interpreters and can be used with the NuttX RTOS
43196
cherry-embedded
cherry-embedded/CherryDAP
CherryDAP is a DAPLink template based on CherryUSB and ARMmbed DAPLink.
29491
wolfSSL
wolfSSL/wolfssl
The wolfSSL library is a small, fast, portable implementation of TLS/SSL for embedded devices to the cloud. wolfSSL supports up to TLS 1.3 and DTLS 1.3! Update to wolfSSL 5.9.1 for the latest CVE fixes.
2.8k91