gpu
64 projects share this GitHub topic
Lines connect members that are measurably related to each other. Dot size reflects stars.
🧬 Members
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
★ 101.7k
fastai
The fastai deep learning library
★ 28.1k
WebGL-Fluid-Simulation
Play with fluids in your browser (works even on mobile)
★ 16.5k
tvm
Open Machine Learning Compiler Framework
★ 13.6k
ai-infra-book
《深入理解 AI Infra：量化分析与系统设计》（李博杰…
★ 7.1k · GitHub ↗
flashinfer
FlashInfer: Kernel Library for LLM Serving
★ 6.8k
lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and…
★ 6k
cuml
cuML - RAPIDS Machine Learning Library
★ 5.2k
llm-d
State of the art inference performance with modern accelerators on Kubernetes
★ 5k
koharu
ML-powered manga translator, written in Rust.
★ 4.9k
MegEngine
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
★ 4.8k
executorch
On-device AI across mobile, embedded and edge for PyTorch
★ 4.8k
tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
★ 4.5k
deepflow
eBPF Observability - Distributed Tracing and Profiling
★ 4.3k
jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
★ 3.2k
heavydb
HeavyDB (formerly MapD/OmniSciDB)
★ 3.1k
chitu
High-performance inference framework for large language models, focusing on efficiency, flexibility, and…
★ 3k
leptonai
A Pythonic framework to simplify AI service building
★ 2.8k
difftaichi
10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)
★ 2.7k
openlake
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training
★ 2.6k
torchrec
Pytorch domain library for recommendation systems
★ 2.6k
deepdetect
Deep Learning Server and CLI for Torch and TensorRT
★ 2.6k
trainer
Distributed AI Model Training and LLM Fine-Tuning on Kubernetes
★ 2.3k
node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model…
★ 2.2k
beta9
Ultrafast serverless GPU inference, sandboxes, and background jobs
★ 1.8k
tt-metal
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
★ 1.7k
glim
GLIM: versatile and extensible point cloud-based 3D localization and mapping framework
★ 1.7k
gpu-hot
🔥 Real-time NVIDIA GPU dashboard
★ 1.6k
uccl
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL…
★ 1.5k
gpu-io
A GPU-accelerated computing library for running physics simulations and other GPGPU computations in a web…
★ 1.5k
isaac_ros_visual_slam
Visual SLAM/odometry package based on NVIDIA-accelerated cuVSLAM
★ 1.4k
gpu_poor
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
★ 1.4k
tty7
The terminal that outlives its window. Shells survive quitting the app, agents can drive other agents, and…
★ 1.3k
modal-examples
Examples of programs built using Modal
★ 1.2k
webgl-wind
Wind power visualization with WebGL particles
★ 1.1k
SiliconScope
Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking
★ 1k · GitHub ↗
Talos
GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over…
★ 988
femtoGPT
Pure Rust implementation of a minimal Generative Pretrained Transformer
★ 935
GPUMD
Graphics Processing Units Molecular Dynamics
★ 811
can-i-finetune-this
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
★ 790
isaac_ros_nvblox
NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox
★ 724
DFloat11
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
★ 642
VerletIntegration
A real-time particle simulation that uses Verlet Integration
★ 581
neurokernel
Neurokernel Project
★ 565
popsift
PopSift is an implementation of the SIFT algorithm in CUDA.
★ 498
blub
3D fluid simulation experiments in Rust, using WebGPU-rs (WIP)
★ 483
isaac_ros_pose_estimation
Deep learned, NVIDIA-accelerated 3D object pose estimation
★ 475
awsome-distributed-ai
Collection of best practices, reference architectures, model training examples and utilities to train large…
★ 473
JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs…
★ 470
warpx
WarpX is an advanced Particle-In-Cell code.
★ 470
zinc
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
★ 467
cucim
cuCIM - RAPIDS GPU-accelerated image processing library
★ 463
hoomd-blue
Molecular dynamics and Monte Carlo soft matter simulation on GPUs.
★ 444
rag-chatbot
RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted…
★ 433
WaterBall
Fluid simulation on a sphere🌏
★ 390
knowhere
Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.
★ 371
SPH_Taichi
A high-performance implementation of SPH in Taichi.
★ 319
mppi_numba
A GPU implementation of Model Predictive Path Integral (MPPI) control that uses a probabilistic…
★ 310
isaac_ros_common
Common utilities, packages, scripts, and testing infrastructure for Isaac ROS packages.
★ 307
attyx
GPU accelerated terminal for agentic workflows
★ 241
llm-inference-capacity-handbook
大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型…
★ 185 · GitHub ↗
kinetograph
A blazingly fast programmatic video engine, made for agents.
★ 172 · GitHub ↗
agentfm-core
AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer.…
★ 138
global-capacity-orchestrator-on-aws
AI/ML and HPC at planetary scale. One API. Every Accelerator. Any Region. MIT-0 licensed
★ 52 · GitHub ↗
🔗 Related families
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.