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.

A public repository collecting links to state-of-the-art training sets, QA, benchmarks and other evaluations for various ML and LLM applications in materials science and chemistry. It includes datasets related to chemistry, materials, multimodal data, and knowledge graphs in the field. The repository aims to provide resources for training and evaluating machine learning models in the materials science and chemistry domains.

Long-Context-Attention (YunChang) is a unified sequence parallel approach that combines the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention to provide a versatile and high-performance solution for long context LLM model training and inference. It addresses the limitations of both methods by offering no limitation on the number of heads, compatibility with advanced parallel strategies, and enhanced performance benchmarks. The tool is verified in Megatron-LM and offers best practices for 4D parallelism, making it suitable for various attention mechanisms and parallel computing advancements.

BIG-Bench Mistake is a dataset of chain-of-thought (CoT) outputs annotated with the location of the first logical mistake. It was released as part of a research paper focusing on benchmarking LLMs in terms of their mistake-finding ability. The dataset includes CoT traces for tasks like Word Sorting, Tracking Shuffled Objects, Logical Deduction, Multistep Arithmetic, and Dyck Languages. Human annotators were recruited to identify mistake steps in these tasks, with automated annotation for Dyck Languages. Each JSONL file contains input questions, steps in the chain of thoughts, model's answer, correct answer, and the index of the first logical mistake.

SUQL (Structured and Unstructured Query Language) is a tool that augments SQL with free text primitives for building chatbots that can interact with relational data sources containing both structured and unstructured information. It seamlessly integrates retrieval models, large language models (LLMs), and traditional SQL to provide a clean interface for hybrid data access. SUQL supports optimizations to minimize expensive LLM calls, scalability to large databases with PostgreSQL, and general SQL operations like JOINs and GROUP BYs.

Graph of Thoughts (GoT) is an official implementation framework designed to solve complex problems by modeling them as a Graph of Operations (GoO) executed with a Large Language Model (LLM) engine. It offers flexibility to implement various approaches like CoT or ToT, allowing users to solve problems using the new GoT approach. The framework includes setup guides, quick start examples, documentation, and examples for users to understand and utilize the tool effectively.

LLM-Geo is an AI-powered geographic information system (GIS) that leverages Large Language Models (LLMs) for automatic spatial data collection, analysis, and visualization. By adopting LLM as the reasoning core, it addresses spatial problems with self-generating, self-organizing, self-verifying, self-executing, and self-growing capabilities. The tool aims to make spatial analysis easier, faster, and more accessible by reducing manual operation time and delivering accurate results through case studies. It uses GPT-4 API in a Python environment and advocates for further research and development in autonomous GIS.

LongRoPE is a method to extend the context window of large language models (LLMs) beyond 2 million tokens. It identifies and exploits non-uniformities in positional embeddings to enable 8x context extension without fine-tuning. The method utilizes a progressive extension strategy with 256k fine-tuning to reach a 2048k context. It adjusts embeddings for shorter contexts to maintain performance within the original window size. LongRoPE has been shown to be effective in maintaining performance across various tasks from 4k to 2048k context lengths.

This repository provides a curated list of open-source projects that implement instruction-tuned large language models (LLMs) with reinforcement learning from human feedback (RLHF). The projects are evaluated in terms of their openness across a predefined set of criteria in the areas of Availability, Documentation, and Access. The goal of this repository is to promote transparency and accountability in the development and deployment of LLMs.

The ByteIR Project is a ByteDance model compilation solution. ByteIR includes compiler, runtime, and frontends, and provides an end-to-end model compilation solution. Although all ByteIR components (compiler/runtime/frontends) are together to provide an end-to-end solution, and all under the same umbrella of this repository, each component technically can perform independently. The name, ByteIR, comes from a legacy purpose internally. The ByteIR project is NOT an IR spec definition project. Instead, in most scenarios, ByteIR directly uses several upstream MLIR dialects and Google Mhlo. Most of ByteIR compiler passes are compatible with the selected upstream MLIR dialects and Google Mhlo.

LLM Hallucination Index - RAG Special is a comprehensive evaluation of large language models (LLMs) focusing on context length and open vs. closed-source attributes. The index explores the impact of context length on model performance and tests the assumption that closed-source LLMs outperform open-source ones. It also investigates the effectiveness of prompting techniques like Chain-of-Note across different context lengths. The evaluation includes 22 models from various brands, analyzing major trends and declaring overall winners based on short, medium, and long context insights. Methodologies involve rigorous testing with different context lengths and prompting techniques to assess models' abilities in handling extensive texts and detecting hallucinations.

This repository implements speculative sampling for large language model (LLM) decoding, utilizing two models - a target model and an approximation model. The approximation model generates token guesses, corrected by the target model, resulting in improved efficiency. It includes implementations of Google's and Deepmind's versions of speculative sampling, supporting models like llama-7B and llama-1B. The tool is designed for fast inference from transformers via speculative decoding.

FedLLM-Bench is a realistic benchmark for the Federated Learning of Large Language Models community. It includes datasets for federated instruction tuning and preference alignment tasks, exhibiting diversities in language, quality, quantity, instruction, sequence length, embedding, and preference. The repository provides training scripts and code for open-ended evaluation, aiming to facilitate research and development in federated learning of large language models.

AIShield Watchtower is a tool designed to fortify the security of AI/ML models and Jupyter notebooks by automating model and notebook discoveries, conducting vulnerability scans, and categorizing risks into 'low,' 'medium,' 'high,' and 'critical' levels. It supports scanning of public GitHub repositories, Hugging Face repositories, AWS S3 buckets, and local systems. The tool generates comprehensive reports, offers a user-friendly interface, and aligns with industry standards like OWASP, MITRE, and CWE. It aims to address the security blind spots surrounding Jupyter notebooks and AI models, providing organizations with a tailored approach to enhancing their security efforts.

OpenSPG is a knowledge graph engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. It provides explicit semantic representations, logical rule definitions, operator frameworks (construction, inference), and other capabilities for domain knowledge graphs. OpenSPG supports pluggable adaptation of basic engines and algorithmic services by various vendors to build customized solutions.

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.

AirGo is a front and rear end separation, multi user, multi protocol proxy service management system, simple and easy to use. It supports vless, vmess, shadowsocks, and hysteria2.

Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. * **Highly performant** : web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O * **Ease of use** : user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing * **Dynamic batching** : aggregate requests from different users for batched inference and distribute results back * **Pipelined stages** : spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads * **Cloud friendly** : designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems * **Do one thing well** : focus on the online serving part, users can pay attention to the model optimization and business logic

The 'llm-code-interpreter' repository is a deprecated plugin that provides a code interpreter on steroids for ChatGPT by E2B. It gives ChatGPT access to a sandboxed cloud environment with capabilities like running any code, accessing Linux OS, installing programs, using filesystem, running processes, and accessing the internet. The plugin exposes commands to run shell commands, read files, and write files, enabling various possibilities such as running different languages, installing programs, starting servers, deploying websites, and more. It is powered by the E2B API and is designed for agents to freely experiment within a sandboxed environment.

Pezzo is a fully cloud-native and open-source LLMOps platform that allows users to observe and monitor AI operations, troubleshoot issues, save costs and latency, collaborate, manage prompts, and deliver AI changes instantly. It supports various clients for prompt management, observability, and caching. Users can run the full Pezzo stack locally using Docker Compose, with prerequisites including Node.js 18+, Docker, and a GraphQL Language Feature Support VSCode Extension. Contributions are welcome, and the source code is available under the Apache 2.0 License.

Learn Cloud Applied Generative AI Engineering (GenEng) is a course focusing on the application of generative AI technologies in various industries. The course covers topics such as the economic impact of generative AI, the role of developers in adopting and integrating generative AI technologies, and the future trends in generative AI. Students will learn about tools like OpenAI API, LangChain, and Pinecone, and how to build and deploy Large Language Models (LLMs) for different applications. The course also explores the convergence of generative AI with Web 3.0 and its potential implications for decentralized intelligence.

This repository contains shared codebase for two projects: gcloud-aio and gcloud-rest. gcloud-aio is built for Python 3's asyncio, while gcloud-rest is a threadsafe requests-based implementation. It provides clients for Google Cloud services like Auth, BigQuery, Datastore, KMS, PubSub, Storage, and Task Queue. Users can install the library using pip and refer to the documentation for usage details. Developers can contribute to the project by following the contribution guide.

Fluid is an open source Kubernetes-native Distributed Dataset Orchestrator and Accelerator for data-intensive applications, such as big data and AI applications. It implements dataset abstraction, scalable cache runtime, automated data operations, elasticity and scheduling, and is runtime platform agnostic. Key concepts include Dataset and Runtime. Prerequisites include Kubernetes version > 1.16, Golang 1.18+, and Helm 3. The tool offers features like accelerating remote file accessing, machine learning, accelerating PVC, preloading dataset, and on-the-fly dataset cache scaling. Contributions are welcomed, and the project is under the Apache 2.0 license with a vendor-neutral approach.

AIGES is a core component of the Athena Serving Framework, designed as a universal encapsulation tool for AI developers to deploy AI algorithm models and engines quickly. By integrating AIGES, you can deploy AI algorithm models and engines rapidly and host them on the Athena Serving Framework, utilizing supporting auxiliary systems for networking, distribution strategies, data processing, etc. The Athena Serving Framework aims to accelerate the cloud service of AI algorithm models and engines, providing multiple guarantees for cloud service stability through cloud-native architecture. You can efficiently and securely deploy, upgrade, scale, operate, and monitor models and engines without focusing on underlying infrastructure and service-related development, governance, and operations.