Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- 2.1k
transcribe.cpp
C/C++ library for running many speech recognition models on ggml
1.3k
- 2.7k
TokenSpeed
LLM serving engine tuned for agentic workloads on datacenter GPUs
- Keller Jordan6k
Modded-NanoGPT
Community speedrun for training a GPT-2-scale model as fast as possible
- Arseny Kapoulkine8.6k
meshoptimizer
C/C++ library for optimizing, simplifying and compressing GPU meshes
- leejet7.7k
stable-diffusion.cpp
C/C++ inference engine for diffusion image and video models
9k
Manjeet Singh7.3k
- 10.3k
DeepEP
GPU communication kernels for expert-parallel MoE training and inference
- 12.4k
CuPy
GPU array library that mirrors the NumPy and SciPy APIs in Python
- 13.1k
FlashMLA
Optimized attention kernels for DeepSeek model inference on GPUs and NPUs
- 15.5k
ggml
Dependency-free C/C++ tensor library for running ML models anywhere
- 132k
llama.cpp
C/C++ engine for running large language models on local hardware
184kOllama
Download and run open language models on your own computer with one command
- Salvatore Sanfilippo24k
DwarfStar
Native C inference engine for running a few large open models locally
- 26k
faster-whisper
Python library for fast Whisper speech transcription on CPU or GPU
- 33.8k
tinygrad
Small, readable deep learning framework with its own kernel compiler
- Andrej58.8k
nanochat
Minimal codebase for training a small chat LLM end to end on one GPU node
- 22.1k
ONNX Runtime
Cross-platform engine for running and training ONNX machine learning models
41.2k