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
107,098 visible repositories in the index
25–48 of 394 · Most stars
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.
TranslatedA local DNS server to obtain the fastest website IP for the best Internet experience, support DoT, DoH, DoQ.
A simple Minecraft clone written in C using modern OpenGL (shaders).
FFmpeg libav tutorial - learn how media works from basic to transmuxing, transcoding and more. Translations: 🇺🇸 🇨🇳 🇰🇷 🇪🇸 🇻🇳 🇧🇷 🇷🇺
Standalone implementation of Zygisk
YugabyteDB - the cloud native distributed SQL database for mission-critical applications.
The source for the Linux kernel used in Windows Subsystem for Linux 2 (WSL2)
The pattern matching swiss knife
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
Unicorn CPU emulator framework (ARM, AArch64, M68K, Mips, Sparc, PowerPC, RiscV, S390x, TriCore, X86)
Windows File System Proxy - FUSE for Windows
TranslatedAlgorithm learning notes
A repository for learning various heap exploitation techniques.
A fast entity component system (ECS) for C & C++
A curated list of Multiplayer Game Network Programming Resources
windows-kernel-exploits Windows平台提权漏洞集合
Open Source Soldering Iron firmware
'Classic' FreeRTOS distribution. Started as Git clone of FreeRTOS SourceForge SVN repo. Submodules the kernel.
Ultra-lightweight JavaScript engine for the Internet of Things.
A customisable 3D platform for agent-based AI research
Simple Proxy Client to force proxy to any Windows/MacOS/Linux Application TCP and UDP traffic
Intel Wi-Fi Drivers for macOS
AFL++ is a state-of-the-art fuzzer, and #1 in benchmarks. It was originally based on AFL. Today it comes with qemu 5.1, collision-free coverage, enhanced laf-intel & redqueen, AFLfast++ power schedules, MOpt mutators, unicorn_mode, and a lot more!
Puffing up reinforcement learning