Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)

A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI

This is the documentation repository for SGLang. It is auto-generated from https://github.com/sgl-project/sglang/tree/main/docs.

它是一个工作流。可快速构建指定架构/平台的docker镜像

Accelerating the development of large multimodal models (LMMs) with lmms-eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Repository of LV-Eval Benchmark

Dynamic MoA

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Development repository for the Triton language and compiler

A framework for few-shot evaluation of autoregressive language models.

including compiler to encode DGL GNN model to instructions, runtime software to transfer data and control the accelerator, and hardware verilog code that can be implemented on FPGA

Geometric Deep Learning Extension Library for PyTorch