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

FlashInfer: Kernel Library for LLM Serving

Cookbook of SGLang - Recipe

Collection of SLURM deployment scripts for various hardware + sglang disaggregation variants

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

A high-throughput and memory-efficient inference and serving engine for LLMs

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

A machine learning compiler for GPUs, CPUs, and ML accelerators

My dotfiles

Flax is a neural network library for JAX that is designed for flexibility.

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

An Open Source Machine Learning Framework for Everyone

A TensorFlow Extension: GPU performance tools for TensorFlow.

Models and examples built with TensorFlow

A visualization tool to display TF-Grappler optimized op graph

Deep Learning for humans

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch