Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
74 repos
-
An open-source inference engine for AI functions in SQL
-
🧱 Experimental library for building inference engines
-
Open ML Compiler Foundation
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
Open ABI and FFI for Machine Learning Systems
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
-
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
-
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
-
UEFI pre-driver NVIDIA GPU unlocker for Windows Linux Hackintosh and all EFI-bootable system (Rust): SEC2 scrubber -> FWSEC/WPR2 -> signed Booter -> V67 four-write payload, read-back verified. Verified on most RTX 20 30 40 Series.
-
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
-
Machine Learning Engineering Open Book
-
Open Machine Learning Compiler Framework
-
kernelboard is the webapp for https://www.gpumode.com
-
JAX in JavaScript – ML library for the web, running on WebGPU & Wasm
-
PantheonSim: GPU simulator for CUDA and ROCm. Run CUDA and HIP programs unmodified on a CPU, no GPU needed: simulated NVIDIA and AMD GPUs for development, teaching and CI.
-
Fork of Apache MXNet 2.0 — runs legacy MXNet code on CUDA 13 / Blackwell (sm_120) GPUs and native Apple Silicon CPU.
-
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
-
Wake and Break: a PSP exploit for AMD navi31 (RX 7900) that makes the card accept unsigned IP firmware. Not persistent: a cold power cycle restores stock.
-
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
-
Apple G13 GPU architecture docs and tools
-
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
-
GPU-accelerated geospatial operations for Apple silicon, built on MLX
-
Automatic formal verification for warp-specialized GPU kernels.
-
If you live in the terminal, kitty is made for you! Cross-platform, fast, feature-rich, GPU based.
-
Lightweight Benchmark Server for Agentic GPU Programming
-
Code-first video & image, rendered natively on WebGPU.
-
A treemap for finding and removing what fills your disk, for Omarchy. Rust + GPUI.
-
A GPU compute-centric 2D renderer.
-
Recast WOOF: GPU weather model (regional, hex and global)
-
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
-
Adaptive robot execution: direct and hybrid controller ports, interaction memory, and EmbodiedSWE/FLUX adapters. CPU validated; GPU qualification pending.
-
Curated high-performance TIRx GPU kernels
-
An Open Compiler Harness for Agentic GPU Programming
-
Compile natural language specs into small neural functions on a single GPU.
-
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
-
Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines
-
Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!
-
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
-
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
-
FlashInfer: Kernel Library for LLM Serving
-
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
-
DeepGEMM: clean and efficient BLAS kernel library on GPU
-
UI components for Omarchy system style
-
The fastai deep learning library
-
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
-
Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF
-
Codex skill for GPU MODE YouTube thumbnails