Starred repositories
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
DLRover: An Automatic Distributed Deep Learning System
nanobind: tiny and efficient C++/Python bindings
Convert .ninja_log files to chrome's about:tracing format.
A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")
Useful shortcuts for bash/zsh
Benchmarking unity builds on real c++ projects.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
Flax is a neural network library for JAX that is designed for flexibility.
Task-based datasets, preprocessing, and evaluation for sequence models.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A tool to classify and statistic GPU kernel information.
📚 Modern C++ Tutorial: C++11 to C++26 On the Fly | https://changkun.de/modern-cpp/
An efficient GPU resource sharing system with fine-grained control for Linux platforms.
NumPy and SciPy on Multi-Node Multi-GPU systems
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
AddressSanitizer, ThreadSanitizer, MemorySanitizer