g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Making LLaVA Tiny via MoE-Knowledge Distillation

Are gradient information useful for pruning of LLMs?

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

Efficient LLM Inference over Long Sequences

Focus on prompting and generating

Mixture-of-Experts for Large Vision-Language Models

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)

Pruning the VLLMs

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

A high-throughput and memory-efficient inference and serving engine for LLMs

VIINA: Violent Incident Information from News Articles on the 2022 Russian Invasion of Ukraine

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

An open-source RAG-based tool for chatting with your documents.

An NVIDIA AI Workbench example project for Retrieval Augmented Generation (RAG)

An Open-Source Package for Information Retrieval

RSL-SQL: Robust Schema Linking in Text-to-SQL Generation

A simple screen parsing tool towards pure vision based GUI agent

Build resilient language agents as graphs.

A MULTI-GENERATOR ENSEMBLE FRAMEWORK FOR NATURAL LANGUAGE TO SQL

More relighting!