Discover

Every project in the index. Underrated first: good projects that haven’t been noticed yet.

31 projects

#gpu-computing library Clear filters

transcribe.cpp
C/C++ library for running many speech recognition models on ggml
AI media AI models and runtimes
2.1k
FlashKDA
CUDA kernels for Kimi Delta Attention on Hopper-class GPUs
AI models and runtimes
1.3k
TokenSpeed
LLM serving engine tuned for agentic workloads on datacenter GPUs
AI models and runtimes Servers and infrastructure
2.7k
Miles
Reinforcement learning framework for post-training large language models
AI models and runtimes
3.2k
LiteRT
On-device runtime for running ML and generative AI models on edge hardware
AI models and runtimes
3.5k
Marin
Open research platform for training large language models end to end
AI models and runtimes Education
4k
Newton
GPU-accelerated, differentiable physics engine for robotics research
Education Hardware and IoT AI models and runtimes
5.8k
AReaL
Asynchronous reinforcement learning system for training LLM agents
AI models and runtimes Agent frameworks and tools
5.9k
ZOZO's Contact Solver
Penetration-free GPU contact simulation for cloth, rods, solids and sand
Design and creative Education
4.6k
LiteRT-LM
On-device LLM runtime for phones, desktops, browsers, and IoT boards
AI models and runtimes
6.7k
vllm-omni
Serving engine for multimodal, diffusion, speech, and action models
AI models and runtimes AI media
7.3k
meshoptimizer
C/C++ library for optimizing, simplifying and compressing GPU meshes
Languages and frameworks Games Design and creative
Arseny Kapoulkine8.6k
slime
Reinforcement learning post-training framework for large language models
AI models and runtimes
8.7k
stable-diffusion.cpp
C/C++ inference engine for diffusion image and video models
AI models and runtimes AI media
leejet7.7k
DeepGEMM
CUDA tensor core kernels for FP8, FP4 and BF16 GEMMs and MoE layers
AI models and runtimes
9k
higgsfield
GPU cluster orchestration and training framework for very large models
AI models and runtimes Servers and infrastructure
6.1k
DeepEP
GPU communication kernels for expert-parallel MoE training and inference
AI models and runtimes
10.3k
LMCache
KV cache layer that stores and reuses LLM attention state across engines
AI models and runtimes Servers and infrastructure
12.1k
CuPy
GPU array library that mirrors the NumPy and SciPy APIs in Python
Languages and frameworks Education AI models and runtimes
12.4k
FlashMLA
Optimized attention kernels for DeepSeek model inference on GPUs and NPUs
AI models and runtimes
13.1k
LongLive
NVIDIA research code for long video generation and robot world models
AI media AI models and runtimes
2.8k
ggml
Dependency-free C/C++ tensor library for running ML models anywhere
AI models and runtimes Languages and frameworks
15.5k
NVIDIA Model Optimizer
Python library for quantizing, pruning, and distilling models for inference
AI models and runtimes
5.4k
KTransformers
CPU-GPU hybrid inference and fine-tuning for large MoE language models
AI models and runtimes
19.6k