This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

ReasonFlux beats o1-preview and DeepSeek-V3 with hierarchical RL and 500 thought templates

Reproduce R1 Zero on Logic Puzzle

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.

Janus-Series: Unified Multimodal Understanding and Generation Models

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

🚴 Call stack profiler for Python. Shows you why your code is slow!

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

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

Frequently used small tools and functions

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A Library for Advanced Deep Time Series Models.

cocotb, a coroutine based cosimulation library for writing VHDL and Verilog testbenches in Python

An NVIDIA AI Workbench example project for fine-tuning a Nemotron-3 8B model

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Installs Vivado on M1/M2 macs

Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

Xilinx FPGA PCIe 保姆级教程 ——基于 PCIe XDMA IP核

Author's PyTorch implementation of TD7 for online and offline RL

Compiler for LightGBM gradient-boosted trees, based on LLVM. Speeds up prediction by ≥10x.