cake

cake is a pure Rust implementation of the llama3 LLM distributed inference based on Candle. The project aims to enable running large models on consumer hardware clusters of iOS, macOS, Linux, and Windows devices by sharding transformer blocks. It allows running inferences on models that wouldn't fit in a single device's GPU memory by batching contiguous transformer blocks on the same worker to minimize latency. The tool provides a way to optimize memory and disk space by splitting the model into smaller bundles for workers, ensuring they only have the necessary data. cake supports various OS, architectures, and accelerations, with different statuses for each configuration.

This project provides a drop-in replacement REST API for Google Cloud Vertex AI (PaLM 2, Codey, Gemini) that is compatible with the OpenAI API specifications. It aims to make Google Cloud Platform Vertex AI more accessible by translating OpenAI API calls to Vertex AI. The software is developed in Python and based on FastAPI and LangChain, designed to be simple and customizable for individual needs. It includes step-by-step guides for deployment, supports various OpenAI API services, and offers configuration through environment variables. Additionally, it provides examples for running locally and usage instructions consistent with the OpenAI API format.

Moatless Tools is a hobby project focused on experimenting with using Large Language Models (LLMs) to edit code in large existing codebases. The project aims to build tools that insert the right context into prompts and handle responses effectively. It utilizes an agentic loop functioning as a finite state machine to transition between states like Search, Identify, PlanToCode, ClarifyChange, and EditCode for code editing tasks.

Call Center AI is an AI-powered call center solution leveraging Azure and OpenAI GPT. It allows for AI agent-initiated phone calls or direct calls to the bot from a configured phone number. The bot is customizable for various industries like insurance, IT support, and customer service, with features such as accessing claim information, conversation history, language change, SMS sending, and more. The project is a proof of concept showcasing the integration of Azure Communication Services, Azure Cognitive Services, and Azure OpenAI for an automated call center solution.

The Snowflake Cortex AI Model Context Protocol (MCP) Server provides tooling for Snowflake Cortex AI, object management, and SQL orchestration. It supports capabilities such as Cortex Search, Cortex Analyst, Cortex Agent, Object Management, SQL Execution, and Semantic View Querying. Users can connect to Snowflake using various authentication methods like username/password, key pair, OAuth, SSO, and MFA. The server is client-agnostic and works with MCP Clients like Claude Desktop, Cursor, fast-agent, Microsoft Visual Studio Code + GitHub Copilot, and Codex. It includes tools for Object Management (creating, dropping, describing, listing objects), SQL Execution (executing SQL statements), and Semantic View Querying (discovering, querying Semantic Views). Troubleshooting can be done using the MCP Inspector tool.

mLoRA (Multi-LoRA Fine-Tune) is an open-source framework for efficient fine-tuning of multiple Large Language Models (LLMs) using LoRA and its variants. It allows concurrent fine-tuning of multiple LoRA adapters with a shared base model, efficient pipeline parallelism algorithm, support for various LoRA variant algorithms, and reinforcement learning preference alignment algorithms. mLoRA helps save computational and memory resources when training multiple adapters simultaneously, achieving high performance on consumer hardware.

This repository contains a Python API for Chat With RTX, which allows users to interact with RTX models for natural language processing. The API provides functionality to send messages and receive responses from various LLM models. It also includes information on the speed of different models supported by Chat With RTX. The repository has a history of updates, including the removal of a feature and the addition of a new model for speech-to-text conversion. The repository is licensed under CC0.

YoMo is an open-source LLM Function Calling Framework for building Geo-distributed AI applications. It is built atop QUIC Transport Protocol and Stateful Serverless architecture, making AI applications low-latency, reliable, secure, and easy. The framework focuses on providing low-latency, secure, stateful serverless functions that can be distributed geographically to bring AI inference closer to end users. It offers features such as low-latency communication, security with TLS v1.3, stateful serverless functions for faster GPU processing, geo-distributed architecture, and a faster-than-real-time codec called Y3. YoMo enables developers to create and deploy stateful serverless functions for AI inference in a distributed manner, ensuring quick responses to user queries from various locations worldwide.

Fira is a memory-efficient training framework for Large Language Models (LLMs) that enables full-rank training under low-rank constraint. It introduces a method for training with full-rank gradients of full-rank weights, achieved with just two lines of equations. The framework includes pre-training and fine-tuning functionalities, packaged as a Python library for easy use. Fira utilizes Adam optimizer by default and provides options for weight decay. It supports pre-training LLaMA models on the C4 dataset and fine-tuning LLaMA-7B models on commonsense reasoning tasks.

SynCode is a novel framework for the grammar-guided generation of Large Language Models (LLMs) that ensures syntactically valid output with respect to defined Context-Free Grammar (CFG) rules. It supports general-purpose programming languages like Python, Go, SQL, JSON, and more, allowing users to define custom grammars using EBNF syntax. The tool compares favorably to other constrained decoders and offers features like fast grammar-guided generation, compatibility with HuggingFace Language Models, and the ability to work with various decoding strategies.

SynCode is a novel framework for the grammar-guided generation of Large Language Models (LLMs) that ensures syntactically valid output based on a Context-Free Grammar (CFG). It supports various programming languages like Python, Go, SQL, Math, JSON, and more. Users can define custom grammars using EBNF syntax. SynCode offers fast generation, seamless integration with HuggingFace Language Models, and the ability to sample with different decoding strategies.

ABQ-LLM is a novel arbitrary bit quantization scheme that achieves excellent performance under various quantization settings while enabling efficient arbitrary bit computation at the inference level. The algorithm supports precise weight-only quantization and weight-activation quantization. It provides pre-trained model weights and a set of out-of-the-box quantization operators for arbitrary bit model inference in modern architectures.

Qwen is a series of large language models developed by Alibaba DAMO Academy. It outperforms the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen models outperform the baseline models of similar model sizes on a series of benchmark datasets, e.g., MMLU, C-Eval, GSM8K, MATH, HumanEval, MBPP, BBH, etc., which evaluate the models’ capabilities on natural language understanding, mathematic problem solving, coding, etc. Qwen-72B achieves better performance than LLaMA2-70B on all tasks and outperforms GPT-3.5 on 7 out of 10 tasks.

This repository contains the code and dataset for LDB, a novel debugging framework that enables Large Language Models (LLMs) to refine their generated programs by tracking the values of intermediate variables throughout the runtime execution. LDB segments programs into basic blocks, allowing LLMs to concentrate on simpler code units, verify correctness block by block, and pinpoint errors efficiently. The tool provides APIs for debugging and generating code with debugging messages, mimicking how human developers debug programs.

The Strands Agents MCP Server is a model-driven approach to building AI agents in just a few lines of code. It provides curated documentation access to GenAI tools via llms.txt files, enabling AI coding assistants to search and retrieve relevant documentation with intelligent ranking. Features include smart document search, curated content indexing, on-demand fetching, snippet generation, and real URL support. The server can be used with various applications that support MCP servers, such as Amazon Q Developer CLI, Anthropic Claude Code, Cline, and Cursor. Users can quickly test the MCP server using the MCP Inspector and follow the provided steps to configure their MCP client and start using the documentation tools. The project welcomes contributions and is licensed under the Apache License 2.0.

xFasterTransformer is an optimized solution for Large Language Models (LLMs) on the X86 platform, providing high performance and scalability for inference on mainstream LLM models. It offers C++ and Python APIs for easy integration, along with example codes and benchmark scripts. Users can prepare models in a different format, convert them, and use the APIs for tasks like encoding input prompts, generating token ids, and serving inference requests. The tool supports various data types and models, and can run in single or multi-rank modes using MPI. A web demo based on Gradio is available for popular LLM models like ChatGLM and Llama2. Benchmark scripts help evaluate model inference performance quickly, and MLServer enables serving with REST and gRPC interfaces.

cake is a pure Rust implementation of the llama3 LLM distributed inference based on Candle. The project aims to enable running large models on consumer hardware clusters of iOS, macOS, Linux, and Windows devices by sharding transformer blocks. It allows running inferences on models that wouldn't fit in a single device's GPU memory by batching contiguous transformer blocks on the same worker to minimize latency. The tool provides a way to optimize memory and disk space by splitting the model into smaller bundles for workers, ensuring they only have the necessary data. cake supports various OS, architectures, and accelerations, with different statuses for each configuration.

llm-export is a tool for exporting llm models to onnx and mnn formats. It has features such as passing onnxruntime correctness tests, optimizing the original code to support dynamic shapes, reducing constant parts, optimizing onnx models using OnnxSlim for performance improvement, and exporting lora weights to onnx and mnn formats. Users can clone the project locally, clone the desired LLM project locally, and use LLMExporter to export the model. The tool supports various export options like exporting the entire model as one onnx model, exporting model segments as multiple models, exporting model vocabulary to a text file, exporting specific model layers like Embedding and lm_head, testing the model with queries, validating onnx model consistency with onnxruntime, converting onnx models to mnn models, and more. Users can specify export paths, skip optimization steps, and merge lora weights before exporting.

LLM-Deploy focuses on the theory and practice of model/LLM reasoning and deployment, aiming to be your partner in mastering the art of LLM reasoning and deployment. Whether you are a newcomer to this field or a senior professional seeking to deepen your skills, you can find the key path to successfully deploy large language models here. The project covers reasoning and deployment theories, model and service optimization practices, and outputs from experienced engineers. It serves as a valuable resource for algorithm engineers and individuals interested in reasoning deployment.

Deep Java Library (DJL) is an open-source, high-level, engine-agnostic Java framework for deep learning. It is designed to be easy to get started with and simple to use for Java developers. DJL provides a native Java development experience and allows users to integrate machine learning and deep learning models with their Java applications. The framework is deep learning engine agnostic, enabling users to switch engines at any point for optimal performance. DJL's ergonomic API interface guides users with best practices to accomplish deep learning tasks, such as running inference and training neural networks.

Caikit is an AI toolkit that enables users to manage models through a set of developer friendly APIs. It provides a consistent format for creating and using AI models against a wide variety of data domains and tasks.

The LiveKit Agent Framework is designed for building real-time, programmable participants that run on servers. Easily tap into LiveKit WebRTC sessions and process or generate audio, video, and data streams. The framework includes plugins for common workflows, such as voice activity detection and speech-to-text. Agents integrates seamlessly with LiveKit server, offloading job queuing and scheduling responsibilities to it. This eliminates the need for additional queuing infrastructure. Agent code developed on your local machine can scale to support thousands of concurrent sessions when deployed to a server in production.

llm-finetuning is a repository that provides a serverless twist to the popular axolotl fine-tuning library using Modal's serverless infrastructure. It allows users to quickly fine-tune any LLM model with state-of-the-art optimizations like Deepspeed ZeRO, LoRA adapters, Flash attention, and Gradient checkpointing. The repository simplifies the fine-tuning process by not exposing all CLI arguments, instead allowing users to specify options in a config file. It supports efficient training and scaling across multiple GPUs, making it suitable for production-ready fine-tuning jobs.

Lean Copilot is a tool that enables the use of large language models (LLMs) in Lean for proof automation. It provides features such as suggesting tactics/premises, searching for proofs, and running inference of LLMs. Users can utilize built-in models from LeanDojo or bring their own models to run locally or on the cloud. The tool supports platforms like Linux, macOS, and Windows WSL, with optional CUDA and cuDNN for GPU acceleration. Advanced users can customize behavior using Tactic APIs and Model APIs. Lean Copilot also allows users to bring their own models through ExternalGenerator or ExternalEncoder. The tool comes with caveats such as occasional crashes and issues with premise selection and proof search. Users can get in touch through GitHub Discussions for questions, bug reports, feature requests, and suggestions. The tool is designed to enhance theorem proving in Lean using LLMs.

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.

Lidar AI Solution is a highly optimized repository for self-driving 3D lidar, providing solutions for sparse convolution, BEVFusion, CenterPoint, OSD, and Conversion. It includes CUDA and TensorRT implementations for various tasks such as 3D sparse convolution, BEVFusion, CenterPoint, PointPillars, V2XFusion, cuOSD, cuPCL, and YUV to RGB conversion. The repository offers easy-to-use solutions, high accuracy, low memory usage, and quantization options for different tasks related to self-driving technology.

This repository showcases how to deploy generative AI models from Amazon SageMaker JumpStart using the AWS CDK. Generative AI is a type of AI that can create new content and ideas, such as conversations, stories, images, videos, and music. The repository provides a detailed guide on deploying image and text generative AI models, utilizing pre-trained models from SageMaker JumpStart. The web application is built on Streamlit and hosted on Amazon ECS with Fargate. It interacts with the SageMaker model endpoints through Lambda functions and Amazon API Gateway. The repository also includes instructions on setting up the AWS CDK application, deploying the stacks, using the models, and viewing the deployed resources on the AWS Management Console.

cake is a pure Rust implementation of the llama3 LLM distributed inference based on Candle. The project aims to enable running large models on consumer hardware clusters of iOS, macOS, Linux, and Windows devices by sharding transformer blocks. It allows running inferences on models that wouldn't fit in a single device's GPU memory by batching contiguous transformer blocks on the same worker to minimize latency. The tool provides a way to optimize memory and disk space by splitting the model into smaller bundles for workers, ensuring they only have the necessary data. cake supports various OS, architectures, and accelerations, with different statuses for each configuration.

Awesome-Robotics-3D is a curated list of 3D Vision papers related to Robotics domain, focusing on large models like LLMs/VLMs. It includes papers on Policy Learning, Pretraining, VLM and LLM, Representations, and Simulations, Datasets, and Benchmarks. The repository is maintained by Zubair Irshad and welcomes contributions and suggestions for adding papers. It serves as a valuable resource for researchers and practitioners in the field of Robotics and Computer Vision.

TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. It enables a data & learning flywheel for LLMs by unifying inference, observability, optimization, and experimentation. The platform includes a high-performance model gateway, structured schema-based inference, observability, experimentation, and data warehouse for analytics. TensorZero Recipes optimize prompts and models, and the platform supports experimentation features and GitOps orchestration for deployment.

This repository provides an easy-to-use solution for running inference servers on Slurm-managed computing clusters using vLLM. All scripts in this repository run natively on the Vector Institute cluster environment. Users can deploy models as Slurm jobs, check server status and performance metrics, and shut down models. The repository also supports launching custom models with specific configurations. Additionally, users can send inference requests and set up an SSH tunnel to run inference from a local device.

Rhesis is a comprehensive test management platform designed for Gen AI teams, offering tools to create, manage, and execute test cases for generative AI applications. It ensures the robustness, reliability, and compliance of AI systems through features like test set management, automated test generation, edge case discovery, compliance validation, integration capabilities, and performance tracking. The platform is open source, emphasizing community-driven development, transparency, extensible architecture, and democratizing AI safety. It includes components such as backend services, frontend applications, SDK for developers, worker services, chatbot applications, and Polyphemus for uncensored LLM service. Rhesis enables users to address challenges unique to testing generative AI applications, such as non-deterministic outputs, hallucinations, edge cases, ethical concerns, and compliance requirements.