Stars
FlatBuffers: Memory Efficient Serialization Library
rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Cross-platform, open-source, Rust-based GPU paravirtualization
Easy flamegraphs for Rust projects and everything else, without Perl or pipes <3
Tool to convert Linux perf files to the profile.proto format used by pprof
Haiku drivers for Nvidia Turing+ GPUs based on official Nvidia kernel driver sources, Mesa NVK Vulkan Driver and Mesa Zink OpenGL driver
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…
An implementation of Tiny Recursive Models (TRM)
Bridges UIKit presentation APIs to a SwiftUI API so you can use presentation controllers, interactive transitions and more.
pizlonator / fil-c
Forked from llvm/llvm-projectFil-C: completely compatible memory safety for C and C++
A TUI and CLI for browsing the On-Line Encyclopedia of Integer Sequences (OEIS) in the terminal.
A SwiftUI, lazy loaded, paging, panning, and zooming view for images and more
FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models. FS-DFM accepted for ICLR 2026
A high-throughput and memory-efficient inference and serving engine for LLMs
Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
Harbor is a framework for running agent evaluations and creating and using RL environments.
React + Dear ImGui + Static Hermes
Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.
Open source implementation of Apple's SwiftUI.
Autonomous GPU Kernel Generation & Optimization via Deep Agents