Open Source AI Accelerator Research Platform Standard / 开源推理研究平台

A minimal PyTorch re-implementation of Qwen 3.8

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.

Inference server benchmarking tool

Preferred Generation Benchmark

Renderer for the harmony response format to be used with gpt-oss

Nano vLLM

The code of several works on oimo.io/works

An Intel 8086 Emulator created in Rust.

Collective communications library with various primitives for multi-machine training.

Pipeline Parallelism for PyTorch

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

The registry of the OptunaHub packages

Python library to use and implement packages in OptunaHub

DiscoGrad - automatically differentiate across conditional branches in C++ programs

A JAX research toolkit for building, editing, and visualizing neural networks.

Development repository for the Triton language and compiler

A curated list for Efficient Large Language Models

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

LLM inference in C/C++

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Code release for NeuS

Google Research

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…

Inference code for Llama models

Extended functionalities for Optuna in combination with third-party libraries.

A curated list of awesome neural radiance fields papers