Efficiently caching Key & Value (KV) tensors is crucial for optimizing LLM inference. Reusing the KV-Cache significantly improves Time To First Token (TTFT) and overall throughput, maximizing system resource-utilization. `llm-d-kv-cache-manager` is a pluggable service enabling KV-Cache Aware Routing for vLLM-based serving platforms, with a high-performance KV-Cache Indexer component tracking KV-Block locality across vLLM pods. It provides intelligent routing for optimal KV-cache-aware placement decisions.

The 'understand-r1-zero' repository focuses on understanding R1-Zero-like training from a critical perspective. It provides insights into base models and reinforcement learning components, highlighting findings and proposing solutions for biased optimization. The repository offers a minimalist recipe for R1-Zero training, detailing the RL-tuning process and achieving state-of-the-art performance with minimal compute resources. It includes codebase, models, and paper related to R1-Zero training implemented with the Oat framework, emphasizing research-friendly and efficient LLM RL techniques.

LLM-Zero-to-Hundred is a repository showcasing various applications of LLM chatbots and providing insights into training and fine-tuning Language Models. It includes projects like WebGPT, RAG-GPT, WebRAGQuery, LLM Full Finetuning, RAG-Master LLamaindex vs Langchain, open-source-RAG-GEMMA, and HUMAIN: Advanced Multimodal, Multitask Chatbot. The projects cover features like ChatGPT-like interaction, RAG capabilities, image generation and understanding, DuckDuckGo integration, summarization, text and voice interaction, and memory access. Tutorials include LLM Function Calling and Visualizing Text Vectorization. The projects have a general structure with folders for README, HELPER, .env, configs, data, src, images, and utils.

Beta9 is an open-source platform for running scalable serverless GPU workloads across cloud providers. It allows users to scale out workloads to thousands of GPU or CPU containers, achieve ultrafast cold-start for custom ML models, automatically scale to zero to pay for only what is used, utilize flexible distributed storage, distribute workloads across multiple cloud providers, and easily deploy task queues and functions using simple Python abstractions. The platform is designed for launching remote serverless containers quickly, featuring a custom, lazy loading image format backed by S3/FUSE, a fast redis-based container scheduling engine, content-addressed storage for caching images and files, and a custom runc container runtime.

JoliGEN is an integrated framework for training custom generative AI image-to-image models. It implements GAN, Diffusion, and Consistency models for various image translation tasks, including domain and style adaptation with conservation of semantics. The tool is designed for real-world applications such as Controlled Image Generation, Augmented Reality, Dataset Smart Augmentation, and Synthetic to Real transforms. JoliGEN allows for fast and stable training with a REST API server for simplified deployment. It offers a wide range of options and parameters with detailed documentation available for models, dataset formats, and data augmentation.

GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

AIGNE Framework is a functional AI application development framework designed to simplify and accelerate the process of building modern applications. It combines functional programming features, powerful artificial intelligence capabilities, and modular design principles to help developers easily create scalable solutions. With key features like modular design, TypeScript support, multiple AI model support, flexible workflow patterns, MCP protocol integration, code execution capabilities, and Blocklet ecosystem integration, AIGNE Framework offers a comprehensive solution for developers. The framework provides various workflow patterns such as Workflow Router, Workflow Sequential, Workflow Concurrency, Workflow Handoff, Workflow Reflection, Workflow Orchestration, Workflow Code Execution, and Workflow Group Chat to address different application scenarios efficiently. It also includes built-in MCP support for running MCP servers and integrating with external MCP servers, along with packages for core functionality, agent library, CLI, and various models like OpenAI, Gemini, Claude, and Nova.

Mooncake is a serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates prefill and decoding clusters, leveraging underutilized CPU, DRAM, and SSD resources of the GPU cluster. Mooncake's scheduler balances throughput and latency-related SLOs, with a prediction-based early rejection policy for highly overloaded scenarios. It excels in long-context scenarios, achieving up to a 525% increase in throughput while handling 75% more requests under real workloads.

Raga LLM Hub is a comprehensive evaluation toolkit for Language and Learning Models (LLMs) with over 100 meticulously designed metrics. It allows developers and organizations to evaluate and compare LLMs effectively, establishing guardrails for LLMs and Retrieval Augmented Generation (RAG) applications. The platform assesses aspects like Relevance & Understanding, Content Quality, Hallucination, Safety & Bias, Context Relevance, Guardrails, and Vulnerability scanning, along with Metric-Based Tests for quantitative analysis. It helps teams identify and fix issues throughout the LLM lifecycle, revolutionizing reliability and trustworthiness.

Genesis is a physics platform designed for general purpose Robotics/Embodied AI/Physical AI applications. It includes a universal physics engine, a lightweight, ultra-fast, pythonic, and user-friendly robotics simulation platform, a powerful and fast photo-realistic rendering system, and a generative data engine that transforms user-prompted natural language description into various modalities of data. It aims to lower the barrier to using physics simulations, unify state-of-the-art physics solvers, and minimize human effort in collecting and generating data for robotics and other domains.

SLAM-LLM is a deep learning toolkit designed for researchers and developers to train custom multimodal large language models (MLLM) focusing on speech, language, audio, and music processing. It provides detailed recipes for training and high-performance checkpoints for inference. The toolkit supports tasks such as automatic speech recognition (ASR), text-to-speech (TTS), visual speech recognition (VSR), automated audio captioning (AAC), spatial audio understanding, and music caption (MC). SLAM-LLM features easy extension to new models and tasks, mixed precision training for faster training with less GPU memory, multi-GPU training with data and model parallelism, and flexible configuration based on Hydra and dataclass.

FinRobot is an open-source AI agent platform designed for financial applications using large language models. It transcends the scope of FinGPT, offering a comprehensive solution that integrates a diverse array of AI technologies. The platform's versatility and adaptability cater to the multifaceted needs of the financial industry. FinRobot's ecosystem is organized into four layers, including Financial AI Agents Layer, Financial LLMs Algorithms Layer, LLMOps and DataOps Layers, and Multi-source LLM Foundation Models Layer. The platform's agent workflow involves Perception, Brain, and Action modules to capture, process, and execute financial data and insights. The Smart Scheduler optimizes model diversity and selection for tasks, managed by components like Director Agent, Agent Registration, Agent Adaptor, and Task Manager. The tool provides a structured file organization with subfolders for agents, data sources, and functional modules, along with installation instructions and hands-on tutorials.

Mobius is an AI infra platform including realtime computing and training. It is built on Ray, a distributed computing framework, and provides a number of features that make it well-suited for online machine learning tasks. These features include: * **Cross Language**: Mobius can run in multiple languages (only Python and Java are supported currently) with high efficiency. You can implement your operator in different languages and run them in one job. * **Single Node Failover**: Mobius has a special failover mechanism that only needs to rollback the failed node itself, in most cases, to recover the job. This is a huge benefit if your job is sensitive about failure recovery time. * **AutoScaling**: Mobius can generate a new graph with different configurations in runtime without stopping the job. * **Fusion Training**: Mobius can combine TensorFlow/Pytorch and streaming, then building an e2e online machine learning pipeline. Mobius is still under development, but it has already been used to power a number of real-world applications, including: * A real-time recommendation system for a major e-commerce company * A fraud detection system for a large financial institution * A personalized news feed for a major news organization If you are interested in using Mobius for your own online machine learning projects, you can find more information in the documentation.

LangGraph Agent with MCP is a toolkit provided by LangChain AI that enables AI agents to interact with external tools and data sources through the Model Context Protocol (MCP). It offers a user-friendly interface for deploying ReAct agents to access various data sources and APIs through MCP tools. The toolkit includes features such as a Streamlit Interface for interaction, Tool Management for adding and configuring MCP tools dynamically, Streaming Responses in real-time, and Conversation History tracking.

veScale is a PyTorch Native LLM Training Framework. It provides a set of tools and components to facilitate the training of large language models (LLMs) using PyTorch. veScale includes features such as 4D parallelism, fast checkpointing, and a CUDA event monitor. It is designed to be scalable and efficient, and it can be used to train LLMs on a variety of hardware platforms.

Efficiently caching Key & Value (KV) tensors is crucial for optimizing LLM inference. Reusing the KV-Cache significantly improves Time To First Token (TTFT) and overall throughput, maximizing system resource-utilization. `llm-d-kv-cache-manager` is a pluggable service enabling KV-Cache Aware Routing for vLLM-based serving platforms, with a high-performance KV-Cache Indexer component tracking KV-Block locality across vLLM pods. It provides intelligent routing for optimal KV-cache-aware placement decisions.

Aiocache is an asyncio cache library that supports multiple backends such as memory, redis, and memcached. It provides a simple interface for functions like add, get, set, multi_get, multi_set, exists, increment, delete, clear, and raw. Users can easily install and use the library for caching data in Python applications. Aiocache allows for easy instantiation of caches and setup of cache aliases for reusing configurations. It also provides support for backends, serializers, and plugins to customize cache operations. The library offers detailed documentation and examples for different use cases and configurations.

ModelBench is a tool for running safety benchmarks against AI models and generating detailed reports. It is part of the MLCommons project and is designed as a proof of concept to aggregate measures, relate them to specific harms, create benchmarks, and produce reports. The tool requires LlamaGuard for evaluating responses and a TogetherAI account for running benchmarks. Users can install ModelBench from GitHub or PyPI, run tests using Poetry, and create benchmarks by providing necessary API keys. The tool generates static HTML pages displaying benchmark scores and allows users to dump raw scores and manage cache for faster runs. ModelBench is aimed at enabling users to test their own models and create tests and benchmarks.

Edgen is a local GenAI API server that serves as a drop-in replacement for OpenAI's API. It provides multi-endpoint support for chat completions and speech-to-text, is model agnostic, offers optimized inference, and features model caching. Built in Rust, Edgen is natively compiled for Windows, MacOS, and Linux, eliminating the need for Docker. It allows users to utilize GenAI locally on their devices for free and with data privacy. With features like session caching, GPU support, and support for various endpoints, Edgen offers a scalable, reliable, and cost-effective solution for running GenAI applications locally.

EasyDist is an automated parallelization system and infrastructure designed for multiple ecosystems. It offers usability by making parallelizing training or inference code effortless with just a single line of change. It ensures ecological compatibility by serving as a centralized source of truth for SPMD rules at the operator-level for various machine learning frameworks. EasyDist decouples auto-parallel algorithms from specific frameworks and IRs, allowing for the development and benchmarking of different auto-parallel algorithms in a flexible manner. The architecture includes MetaOp, MetaIR, and the ShardCombine Algorithm for SPMD sharding rules without manual annotations.

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on LLMs inference and serving.

LLM-Viewer is a tool for visualizing Language and Learning Models (LLMs) and analyzing performance on different hardware platforms. It enables network-wise analysis, considering factors such as peak memory consumption and total inference time cost. With LLM-Viewer, users can gain valuable insights into LLM inference and performance optimization. The tool can be used in a web browser or as a command line interface (CLI) for easy configuration and visualization. The ongoing project aims to enhance features like showing tensor shapes, expanding hardware platform compatibility, and supporting more LLMs with manual model graph configuration.

ServerlessLLM is a fast, affordable, and easy-to-use library designed for multi-LLM serving, optimized for environments with limited GPU resources. It supports loading various leading LLM inference libraries, achieving fast load times, and reducing model switching overhead. The library facilitates easy deployment via Ray Cluster and Kubernetes, integrates with the OpenAI Query API, and is actively maintained by contributors.

llm-resource is a comprehensive collection of high-quality resources for Large Language Models (LLM). It covers various aspects of LLM including algorithms, training, fine-tuning, alignment, inference, data engineering, compression, evaluation, prompt engineering, AI frameworks, AI basics, AI infrastructure, AI compilers, LLM application development, LLM operations, AI systems, and practical implementations. The repository aims to gather and share valuable resources related to LLM for the community to benefit from.

LitServe is a high-throughput serving engine designed for deploying AI models at scale. It generates an API endpoint for models, handles batching, streaming, and autoscaling across CPU/GPUs. LitServe is built for enterprise scale with a focus on minimal, hackable code-base without bloat. It supports various model types like LLMs, vision, time-series, and works with frameworks like PyTorch, JAX, Tensorflow, and more. The tool allows users to focus on model performance rather than serving boilerplate, providing full control and flexibility.

This repository documents how to optimize common algorithms based on CUDA. It includes subdirectories with code implementations for specific optimizations. The optimizations cover topics such as compiling PyTorch from source, NVIDIA's reduce optimization, OneFlow's elementwise template, fast atomic add for half data types, upsample nearest2d optimization in OneFlow, optimized indexing in PyTorch, OneFlow's softmax kernel, linear attention optimization, and more. The repository also includes learning resources related to deep learning frameworks, compilers, and optimization techniques.

AIAC is a library and command line tool to generate Infrastructure as Code (IaC) templates, configurations, utilities, queries, and more via LLM providers such as OpenAI, Amazon Bedrock, and Ollama. Users can define multiple 'backends' targeting different LLM providers and environments using a simple configuration file. The tool allows users to ask a model to generate templates for different scenarios and composes an appropriate request to the selected provider, storing the resulting code to a file and/or printing it to standard output.

ENOVA is an open-source service for Large Language Model (LLM) deployment, monitoring, injection, and auto-scaling. It addresses challenges in deploying stable serverless LLM services on GPU clusters with auto-scaling by deconstructing the LLM service execution process and providing configuration recommendations and performance detection. Users can build and deploy LLM with few command lines, recommend optimal computing resources, experience LLM performance, observe operating status, achieve load balancing, and more. ENOVA ensures stable operation, cost-effectiveness, efficiency, and strong scalability of LLM services.

Jina is a tool that allows users to build multimodal AI services and pipelines using cloud-native technologies. It provides a Pythonic experience for serving ML models and transitioning from local deployment to advanced orchestration frameworks like Docker-Compose, Kubernetes, or Jina AI Cloud. Users can build and serve models for any data type and deep learning framework, design high-performance services with easy scaling, serve LLM models while streaming their output, integrate with Docker containers via Executor Hub, and host on CPU/GPU using Jina AI Cloud. Jina also offers advanced orchestration and scaling capabilities, a smooth transition to the cloud, and easy scalability and concurrency features for applications. Users can deploy to their own cloud or system with Kubernetes and Docker Compose integration, and even deploy to JCloud for autoscaling and monitoring.

Vidur is a high-fidelity and extensible LLM inference simulator designed for capacity planning, deployment configuration optimization, testing new research ideas, and studying system performance of models under different workloads and configurations. It supports various models and devices, offers chrome trace exports, and can be set up using mamba, venv, or conda. Users can run the simulator with various parameters and monitor metrics using wandb. Contributions are welcome, subject to a Contributor License Agreement and adherence to the Microsoft Open Source Code of Conduct.

AI System School is a curated list of research in machine learning systems, focusing on ML/DL infra, LLM infra, domain-specific infra, ML/LLM conferences, and general resources. It provides resources such as data processing, training systems, video systems, autoML systems, and more. The repository aims to help users navigate the landscape of AI systems and machine learning infrastructure, offering insights into conferences, surveys, books, videos, courses, and blogs related to the field.