Highlights
- All languages
- ANTLR
- ASL
- ApacheConf
- Assembly
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Common Workflow Language
- Crystal
- Cuda
- Cython
- D
- DIGITAL Command Language
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- GDScript
- GLSL
- Gherkin
- Go
- Groovy
- HTML
- Handlebars
- Haskell
- Haxe
- Java
- JavaScript
- JetBrains MPS
- Jinja
- Jsonnet
- Julia
- Jupyter Notebook
- Just
- Kotlin
- Less
- Lua
- M4
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Meson
- NSIS
- Nim
- Nix
- OCaml
- Objective-C
- Objective-C++
- Objective-J
- PHP
- PLpgSQL
- Pawn
- Perl
- Pony
- PostScript
- PowerShell
- Prolog
- Pug
- PureScript
- Python
- QML
- R
- Racket
- Reason
- Rocq Prover
- Roff
- Ruby
- Rust
- SCSS
- SRecode Template
- Scala
- Scheme
- Shell
- Smali
- Starlark
- Svelte
- Swift
- SystemVerilog
- TSQL
- Tcl
- TeX
- TypeScript
- TypeSpec
- V
- VHDL
- Vala
- Verilog
- Vim Script
- Vim Snippet
- Visual Basic .NET
- Vue
- XML
- Zig
- eC
- hoon
- jq
Starred repositories
CUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA te…
Public repository of the Micro QuickJS Javascript Engine
DeepSeek Coder: Let the Code Write Itself
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
stephencwelch / manim_videos
Forked from 3b1b/videosCode for the manim-generated scenes used in welch labs videos
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
A Rust implementation of Andrej Karpathy's micrograd engine.
An autoregressive character-level language model for making more things
AI-powered video object removal (diffusion inpainting under the hood).
An open-source AI agent that brings the power of Gemini directly into your terminal.
Full-throttle, wire-speed hardware implementation of Wireguard VPN, using low-cost Artix7 FPGA with opensource toolchain. If you seek security and privacy, nothing is private in our codebase. Our d…
An transformer based LLM. Written completely in Rust
Kimi K2 is the large language model series developed by Moonshot AI team
A full attention mechanism and transformer in pure go.
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient Multi-head Latent Attention Kernels
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
AI-augmented development in Vim and Neovim