Awesome GitHub RepositoriesInference Optimization

TensorFlow is a comprehensive machine learning framework designed for the construction, training, and deployment of complex mathematical models. It utilizes a graph-based execution model that represents operations as directed acyclic graphs, enabling automatic differentiation and efficient parallel processing. The system provides high-level interfaces for defining neural network architectures, alongside a robust engine for managing multidimensional array structures and tensor mathematics. The framework distinguishes itself through a scalable distributed runtime that orchestrates workloads acr

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

vLLM is a high-throughput inference engine designed for the efficient serving and execution of large language models. It functions as a production-ready distributed model server, providing standard API protocols for online serving while also supporting offline batch processing. The system is built to maximize token generation speed and memory efficiency, enabling both large-scale cloud deployments and local execution on personal hardware. The project distinguishes itself through advanced memory management and request scheduling techniques, most notably its use of non-contiguous key-value cach

PaddleOCR is a comprehensive optical character recognition framework designed for detecting and transcribing text from images and documents into structured, machine-readable formats. It provides a modular computer vision pipeline that decouples image preprocessing, text detection, and character recognition into independent, configurable stages. This architecture supports automated document digitization and multilingual text recognition, capable of identifying text in over one hundred languages across diverse environments ranging from scanned documents to industrial scenes. The framework disti

Unsloth is a high-performance training and inference platform designed to optimize the lifecycle of large language and multimodal models. It provides a comprehensive engine for fine-tuning, executing, and managing models locally, with a focus on reducing memory consumption and increasing compute speed on consumer-grade hardware. The platform distinguishes itself through hand-optimized kernels and automated computational graph techniques that maximize hardware throughput. It supports advanced training methodologies, including reinforcement learning for reasoning and efficient adapter-based fin

Llama is a large language model runtime and inference engine designed to load and execute autoregressive transformer models. It enables the generation of natural language text completions from prompts using pretrained weights. The system features multi-GPU model parallelism, which distributes model weights and workloads across multiple graphics processors to support larger parameter counts. It also incorporates a content safety filter that uses classifiers to intercept and block unsafe inputs or outputs during the inference process. The project covers broad capabilities in distributed model

Llama is a computational framework and runtime environment designed for executing transformer-based neural networks locally. It functions as a generative AI inference engine, enabling the processing of input sequences through pre-trained model weights to produce text completions and structured data outputs directly on your own hardware. The system distinguishes itself through specialized memory and computation management techniques, including memory-mapped weight loading and quantization-aware inference, which allow for efficient execution on standard consumer hardware. It utilizes a stateles

YOLOv5 is a comprehensive computer vision framework designed for end-to-end deep learning, specializing in real-time object detection, image classification, and instance segmentation. It provides a unified toolkit that manages the entire lifecycle of a model, from initial dataset configuration and hyperparameter tuning to high-speed inference and deployment. The framework utilizes a modular neural architecture, allowing users to swap backbone and head components to tailor models for specific visual tasks. What distinguishes this project is its focus on production-ready deployment and model ef

Grok-1 is an open-weights large language model implementation featuring a sparse mixture-of-experts architecture. It is designed for high-performance text generation and natural language processing by activating only a subset of specialized expert layers per token. The model utilizes 8-bit weight quantization to reduce memory overhead and accelerate loading. To manage its high parameter count, the implementation supports activation sharding, which distributes the memory load across multiple hardware devices during execution. The project covers large-scale model inference, including text comp

whisper.cpp is a C++ implementation of the Whisper speech-to-text model, serving as a lightweight machine learning inference engine and quantized runtime. It provides high-performance automatic speech recognition and real-time audio transcription without requiring a Python environment. The project utilizes model quantization to reduce memory usage and increase inference speed on local hardware. It incorporates hardware acceleration to optimize processing speed across different processors. The system covers audio processing capabilities including voice activity detection, speaker diarization,

VoxCPM is a multilingual speech synthesis system and text-to-speech inference server. It functions as an AI voice cloning tool and a synthetic voice designer, capable of generating natural speech across global languages and regional dialects using a GPU-accelerated audio generator. The project features a speech model fine-tuning framework that supports both full parameter updates and low-rank adaptation for customizing voice characteristics. It enables high-fidelity voice cloning from reference audio, including cross-lingual voice transfer and acoustic environment mimicry, as well as the crea

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

Darknet is a low-level neural network engine and framework written in C. It is designed for training and deploying deep learning models, with a primary focus on convolutional neural networks. The project serves as a CUDA accelerated deep learning library that offloads heavy mathematical operations to NVIDIA graphics hardware. This acceleration is used to increase processing speed and reduce execution time during the training of large networks. The engine supports a range of activities including deep learning research, image recognition development, and the training of convolutional neural ne

Flux is a diffusion model inference engine designed for text-to-image generation and image-to-image manipulation. It provides a system for executing open-weight models to transform natural language descriptions into visual imagery or to modify existing images. The project distinguishes itself through a flow-matching framework for image generation and a structural image controller. This controller allows for guided synthesis by using depth maps and Canny edge detection to constrain the geometry and composition of the output. The toolkit covers a broad range of image editing capabilities, incl

llamafile is a model bundler and local runtime that packages large language models and their execution logic into single, portable executable files. It provides a distribution format for zero-installation local execution, allowing users to run models on various operating systems without managing external library dependencies or environment configurations. The project differentiates itself by bundling model weights and the runtime into one self-extracting binary. This approach simplifies the distribution of AI models, as the combined file contains everything necessary to run the model immediat

Llamafile is a machine learning model runner and packager that enables local inference by bundling model weights and runtime environments into a single, self-contained executable. It functions as a cross-platform engine, allowing users to execute large language models and perform speech-to-text tasks directly on their own hardware without requiring external software dependencies or complex installations. The project distinguishes itself by utilizing a specialized binary format that allows the same executable to run natively across multiple operating systems and hardware architectures. It auto

verl is a distributed training system designed for large language model alignment and reinforcement learning. It provides a framework for executing post-training pipelines, including supervised fine-tuning and reinforcement learning from human feedback, to refine model behavior and agentic capabilities. The system utilizes a hybrid training and inference engine that optimizes memory and communication when switching between model generation and gradient updates. It supports multi-modal reinforcement learning for models processing both image and text data, and implements algorithms such as PPO

This project is a comprehensive framework and toolkit for developing, optimizing, and deploying transformer-based models across multimodal, document intelligence, and natural language processing tasks. It provides a unified neural architecture that processes text, vision, audio, and document layout data through a shared set of weights, enabling researchers and developers to build foundational models that align cross-modal representations. The platform distinguishes itself through advanced training and inference strategies designed for large-scale deep learning. It incorporates specialized mec

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

This project is a comprehensive educational framework designed to teach the design, deployment, and performance optimization of machine learning systems. It provides a structured curriculum that covers the full stack of artificial intelligence engineering, ranging from the construction of core framework components like tensors and automatic differentiation engines to the orchestration of large-scale distributed training clusters. The platform distinguishes itself through its integration of physics-grounded systems modeling and interactive simulation environments. Users can experiment with dis