Best AI tools for< Cache Activations >

DataGPT is a conversational AI data analyst that provides instant analysis and answers to any data-related question in everyday language. It connects to any data source and automatically defines and suggests the most relevant metrics and dimensions. DataGPT's core analytics engine carries out intricate analysis against all data, checking every segment, identifying anomalies, detecting outliers, diving into funnel analytics, or conducting robust comparative analysis to reveal accurate results. The AI-powered onboarding agent guides users through the setup process, and the Lightning Cache boosts query speeds 100x over current data warehouses. The Data Navigator allows users to freely explore any part of their data with just a few clicks. DataGPT empowers decision-makers by replacing specialized dashboards with an 'ask me anything' interface, enabling them to access essential insights on demand.

imgix is an end-to-end visual media solution that enables users to create, transform, and optimize captivating images and videos for an unparalleled visual experience. It simplifies the complex visual media technology, improves web performance, and delivers responsive design. Trusted by innovative companies worldwide, imgix offers features such as easy cloud storage connection, intelligent compression, fast loading with a globally distributed CDN, over 150 image operations, video streaming, asset management, intuitive analytics, and powerful SDKs & tools.

ChatBA is a generative AI tool designed for creating slides. It utilizes AI technology to assist users in generating content for their presentation slides. Due to high demand, the tool is currently reaching account limits of the OpenAI API. Users can still explore example prompts that are cached on the platform. ChatBA aims to simplify the process of creating engaging and informative slides by leveraging the power of artificial intelligence.

abliterator.py is a simple Python library/structure designed to ablate features in large language models (LLMs) supported by TransformerLens. It provides capabilities to enter temporary contexts, cache activations with N samples, calculate refusal directions, and includes tokenizer utilities. The library aims to streamline the process of experimenting with ablation direction turns by encapsulating useful logic and minimizing code complexity. While currently basic and lacking comprehensive documentation, the library serves well for personal workflows and aims to expand beyond feature ablation to augmentation and additional features over time with community support.

Awesome-LLM-Quantization is a curated list of resources related to quantization techniques for Large Language Models (LLMs). Quantization is a crucial step in deploying LLMs on resource-constrained devices, such as mobile phones or edge devices, by reducing the model's size and computational requirements.

This repository contains the training code of LLM-QAT for large language models. The work investigates quantization-aware training for LLMs, including quantizing weights, activations, and the KV cache. Experiments were conducted on LLaMA models of sizes 7B, 13B, and 30B, at quantization levels down to 4-bits. Significant improvements were observed when quantizing weight, activations, and kv cache to 4-bit, 8-bit, and 4-bit, respectively.

Official PyTorch implementation of Wanda (Pruning by Weights and Activations), a simple and effective pruning approach for large language models. The pruning approach removes weights on a per-output basis, by the product of weight magnitudes and input activation norms. The repository provides support for various features such as LLaMA-2, ablation study on OBS weight update, zero-shot evaluation, and speedup evaluation. Users can replicate main results from the paper using provided bash commands. The tool aims to enhance the efficiency and performance of language models through structured and unstructured sparsity techniques.

QServe is a serving system designed for efficient and accurate Large Language Models (LLM) on GPUs with W4A8KV4 quantization. It achieves higher throughput compared to leading industry solutions, allowing users to achieve A100-level throughput on cheaper L40S GPUs. The system introduces the QoQ quantization algorithm with 4-bit weight, 8-bit activation, and 4-bit KV cache, addressing runtime overhead challenges. QServe improves serving throughput for various LLM models by implementing compute-aware weight reordering, register-level parallelism, and fused attention memory-bound techniques.

Awesome-Efficient-LLM is a curated list focusing on efficient large language models. It includes topics such as knowledge distillation, network pruning, quantization, inference acceleration, efficient MOE, efficient architecture of LLM, KV cache compression, text compression, low-rank decomposition, hardware/system, tuning, and survey. The repository provides a collection of papers and projects related to improving the efficiency of large language models through various techniques like sparsity, quantization, and compression.

SpinQuant is a tool designed for LLM quantization with learned rotations. It focuses on optimizing rotation matrices to enhance the performance of quantized models, narrowing the accuracy gap to full precision models. The tool implements rotation optimization and PTQ evaluation with optimized rotation, providing arguments for model name, batch sizes, quantization bits, and rotation options. SpinQuant is based on the findings that rotation helps in removing outliers and improving quantization, with specific enhancements achieved through learning rotation with Cayley optimization.

Awesome LLM compression research papers and tools to accelerate LLM training and inference.

Marlin is a highly optimized FP16xINT4 matmul kernel designed for large language model (LLM) inference, offering close to ideal speedups up to batchsizes of 16-32 tokens. It is suitable for larger-scale serving, speculative decoding, and advanced multi-inference schemes like CoT-Majority. Marlin achieves optimal performance by utilizing various techniques and optimizations to fully leverage GPU resources, ensuring efficient computation and memory management.

ZML is a high-performance AI inference stack built for production, using Zig language, MLIR, and Bazel. It allows users to create exciting AI projects, run pre-packaged models like MNIST, TinyLlama, OpenLLama, and Meta Llama, and compile models for accelerator runtimes. Users can also run tests, explore examples, and contribute to the project. ZML is licensed under the Apache 2.0 license.

Awesome-LLM-Inference: A curated list of 📙Awesome LLM Inference Papers with Codes, check 📖Contents for more details. This repo is still updated frequently ~ 👨‍💻‍ Welcome to star ⭐️ or submit a PR to this repo!

llm-analysis is a tool designed for Latency and Memory Analysis of Transformer Models for Training and Inference. It automates the calculation of training or inference latency and memory usage for Large Language Models (LLMs) or Transformers based on specified model, GPU, data type, and parallelism configurations. The tool helps users to experiment with different setups theoretically, understand system performance, and optimize training/inference scenarios. It supports various parallelism schemes, communication methods, activation recomputation options, data types, and fine-tuning strategies. Users can integrate llm-analysis in their code using the `LLMAnalysis` class or use the provided entry point functions for command line interface. The tool provides lower-bound estimations of memory usage and latency, and aims to assist in achieving feasible and optimal setups for training or inference.

AirLLM is a tool that optimizes inference memory usage, enabling large language models to run on low-end GPUs without quantization, distillation, or pruning. It supports models like Llama3.1 on 8GB VRAM. The tool offers model compression for up to 3x inference speedup with minimal accuracy loss. Users can specify compression levels, profiling modes, and other configurations when initializing models. AirLLM also supports prefetching and disk space management. It provides examples and notebooks for easy implementation and usage.

The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑‍🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

LLM-PowerHouse is a comprehensive and curated guide designed to empower developers, researchers, and enthusiasts to harness the true capabilities of Large Language Models (LLMs) and build intelligent applications that push the boundaries of natural language understanding. This GitHub repository provides in-depth articles, codebase mastery, LLM PlayLab, and resources for cost analysis and network visualization. It covers various aspects of LLMs, including NLP, models, training, evaluation metrics, open LLMs, and more. The repository also includes a collection of code examples and tutorials to help users build and deploy LLM-based applications.

This repo contains a comprehensive paper list of **Model Quantization** for efficient deep learning on AI conferences/journals/arXiv. As a highlight, we categorize the papers in terms of model structures and application scenarios, and label the quantization methods with keywords.

The worker-vLLM repository provides a serverless endpoint for deploying OpenAI-compatible vLLM models with blazing-fast performance. It supports deploying various model architectures, such as Aquila, Baichuan, BLOOM, ChatGLM, Command-R, DBRX, DeciLM, Falcon, Gemma, GPT-2, GPT BigCode, GPT-J, GPT-NeoX, InternLM, Jais, LLaMA, MiniCPM, Mistral, Mixtral, MPT, OLMo, OPT, Orion, Phi, Phi-3, Qwen, Qwen2, Qwen2MoE, StableLM, Starcoder2, Xverse, and Yi. Users can deploy models using pre-built Docker images or build custom images with specified arguments. The repository also supports OpenAI compatibility for chat completions, completions, and models, with customizable input parameters. Users can modify their OpenAI codebase to use the deployed vLLM worker and access a list of available models for deployment.

Gollama is a tool designed for managing Ollama models through a Text User Interface (TUI). Users can list, inspect, delete, copy, and push Ollama models, as well as link them to LM Studio. The application offers interactive model selection, sorting by various criteria, and actions using hotkeys. It provides features like sorting and filtering capabilities, displaying model metadata, model linking, copying, pushing, and more. Gollama aims to be user-friendly and useful for managing models, especially for cleaning up old models.

Specialist for technical and editorial TYPO3 support. // FEATURES: Optional browsing via external api with 'web: search query' and optimized GitHub access.

Genera la imágen del coche de tus sueños