A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Repository Index
103,113 visible repositories in the index
1–16 of 16 · Most stars
Inference Llama 2 in one file of pure C
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
Locally run an Instruction-Tuned Chat-Style LLM
Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
- llama
- alpaca
- chinese
- vicuna
Modern, secure, portable, multiprotocol bootloader and boot manager.
- bootloader
- bios
- x86
- x86-64
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
llama and other large language models on iOS and MacOS offline using GGML library.
- ai
- ggml
- gpt-2
- gptneox
Python bindings for the Transformer models implemented in C/C++ using GGML library.
- ai
- llm
- transformers
- ctransformers
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
- rdma
- hpc
- networking
- infiniband
This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
- asr
- ctranslate2
- huggingface
- whisper
maxxing the ability to run different LLMs on the smallest devices possible
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
Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.