Junrong Lin

SGLang is a fast serving framework for large language models and vision language models.

veRL: Volcano Engine Reinforcement Learning for LLM

No description.

Fast and memory-efficient exact attention

something for my personal development env setup

使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer

Train the smallest LM you can that fits in 16MB. Best model wins!

A unified inference and post-training framework for accelerated video generation.

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Helpful kernel tutorials and examples for tile-based GPU programming

For https://mlsys26.flashinfer.ai/

[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training

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

DeepEP: an efficient expert-parallel communication library

My learning notes/codes for ML SYS.

An intuitive and low-overhead instrumentation tool for Python

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.

Allow torch tensor memory to be released and resumed later

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

No description.

Development repository for the Triton language and compiler

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

Build AI-powered applications with React, Svelte, Vue, and Solid

Tensors and Dynamic neural networks in Python with strong GPU acceleration

🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society

No description.

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust to everyone.

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

No description.