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

A framework for the evaluation of autoregressive code generation language models.

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

EvalPlus for rigourous evaluation of LLM-synthesized code

Automatic DNN generation for fuzzing and more.

A telegram bot that sends you a message when the GPU is in use

Artifact for ESEC/FSE'23 paper "NeuRI: Diversifying DNN Generation via Inductive Rule Inference"

Python package designed for single-cell calling cards data

FuzzBench - Fuzzer benchmarking as a service.

OSS-Fuzz - continuous fuzzing for open source software.

The Lepton AI SDK to make building AI applications simple.

Apache Commons Collections

Inference code for CodeLlama models

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

An Open Source Machine Learning Framework for Everyone

A list of awesome compiler projects and papers for tensor computation and deep learning.

Automatic Mapping Generation, Verification, and Exploration for ISA-based Spatial Accelerators

relax << ganler

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator