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…

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

A Comprehensive Assessment of Trustworthiness in GPT Models

FLINT (Fast Library for Number Theory)

A WebUI app for Music-Source-Separation-Training and we packed UVR together!

AI Agent Framework, the Pydantic way

Open Source Continuous Inference Benchmark Research Platform Kimi K2.6, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3

A curated list of awesome leaderboard-oriented resources for AI domain

Kora is an experimental high-performance, type-safe, lifecycle-driven, effect-based JVM runtime for service execution, with out-and-out descriptive DSL.

A Neural Framework for MT Evaluation

🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

FSA/FST algorithms, differentiable, with PyTorch compatibility.

Commandline tool for automated downloads of echo360 videos hosted by university

A fast, lightweight, and extensible RWKV chat UI powered by Flutter. Offline-ready, multi-backend support, ideal for local RWKV inference.

Codebase for decoding compressed trust.

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

DeepSeek网页端API代理，支持OpenAI与Anthropic兼容接口 | OpenAI & Anthropic compatible API proxy for DeepSeek web

A GPU-Z inspired diagnostic tool for Linux. GPU-T provides detailed hardware specs, real-time sensors, and advanced diagnostics for AMD and NVIDIA GPUs (Intel support planned). Built with .NET & Av…

RWKV-7 7.2B fp16 15000+ tps decoding @ single 5090

MessagePack serializer implementation for Python msgpack.org[Python]

GitHub’s official command line tool

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Generative Adaptive MIDI Extractor

Kode CLI — Design for post-human workflows. One unit agent for every human & computer task.

An educational AI coding agent CLI

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…