- All languages
- Assembly
- C
- C#
- C++
- CMake
- CSS
- CoffeeScript
- Cuda
- Dart
- Dockerfile
- Emacs Lisp
- Go
- HTML
- Java
- JavaScript
- Jsonnet
- Julia
- Jupyter Notebook
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Mojo
- PHP
- Perl
- PostScript
- Python
- Rich Text Format
- Ruby
- Rust
- SCSS
- Scheme
- Shell
- Svelte
- Swift
- SystemVerilog
- TeX
- TypeScript
- Typst
- Vim Script
- Vue
Starred repositories
Formal verification workflow and skill stack for coding agents (TLA+, Z3, Apalache, TLAPS)
Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scratch. Kubernetes-native checkpoint & restore that runs along…
知了 Cicada · 任何会议和直播的实时字幕、同声传译、AI 会议纪要,Mac、Windows、Linux、Android 免费开源。Live subtitles, interpreting and meeting notes for any call or stream, on Mac, Windows, Linux and Android.
The animation engine for agents: blazingly fast math and 3D videos with Manim's Python API, on a Rust GPU core.
An Open Compiler Harness for Agentic GPU Programming
Community wishlist for reproducible kernel definitions, workloads, and validated optimized solutions.
High-performance GPU kernels for Ads and Recsys model training, independently implemented and optimized for real-world workloads and model-specific input characteristics.
Minimal agent harness in one Bash file. One-line quick start. Bootloader agent for bare-metal servers.
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
NVFP4 Flash-Attention 4 on BlackWell
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
Multimodal RL training framework for diffusion & omni models
Specular: An agentic tool for finding deep bugs in system code using TLA+
PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for evaluation of training and inference platforms.
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
An easy-to-use framework for large scale recommendation algorithms.
无线麦(SayAll.app):支持小米蓝牙遥控器 2 和 2 Pro,变成 Mac 语音输入设备
A hybrid GPU cluster simulator for ML system performance estimation
Fully chunked KL-Loss kernel, that massively reduces VRAM usage
a static analytical model for LLM distributed training
Exemplar Performance provides recipes in ready-to-use templates for evaluating performance of specific AI use cases across hardware and software combinations.
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++