A light weight vLLM simulator, for mocking out replicas.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

slime is an LLM post-training framework for RL Scaling.

Open-source, secure environment with real-world tools for enterprise-grade agents.

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

Python framework for creating, editing, and running Noisy Intermediate-Scale Quantum (NISQ) circuits.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

A debugging and profiling tool that can trace and visualize python code execution

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

An open-source AI agent that brings the power of Gemini directly into your terminal.

A Quirky Assortment of CuTe Kernels

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

kernels, of the mega variety

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

DeepSeek-V3/R1 inference performance simulator

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

The official repository for the gem5 computer-system architecture simulator.

A lightweight design for computation-communication overlap.

A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.

LLM training in simple, raw C/CUDA