FlashMLA: Efficient Multi-head Latent Attention Kernels

DeepSeek-VL: Towards Real-World Vision-Language Understanding

🩹Editing large language models within 10 seconds⚡

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Traditional Mandarin LLMs for Taiwan

Gemma open-weight LLM library, from Google DeepMind

Official implementation for "Ham2Pose: Animating Sign Language Notation into Pose Sequences" [CVPR 2023]

Effortless Real-Time Sign Language Translation

Code release for ConvNeXt V2 model

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

LLM inference in C/C++

Repository accompanying the "Sign Pose-based Transformer for Word-level Sign Language Recognition" paper

The Cloud-Native API Gateway and AI Gateway

【C++面试&C++学习指南】 这里整理了C++后端研发工程师面试和工作必备的知识点 。

Material for the SciPy 2017 Cython tutorial

The most widely used Python to C compiler

Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies

在 MPV 觀看巴哈姆特動畫瘋時，可以支援彈幕列表

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

All materials you need for Federated Learning: blogs, videos, papers, and softwares, etc.

A scalable Eyeriss model in SystemC.

Macro Placement - benchmarks, evaluators, and reproducible results from leading methods in open source

NVIDIA Federated Learning Application Runtime Environment

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

implement byol in cifar-10

A complete computer science study plan to become a software engineer.