Search Results for "inference engine"
Sort By:
Showing 31 open source projects for "inference engine"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. -
2
vLLM
A high-throughput and memory-efficient inference and serving engine
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more. -
3
SimpleLLM
950 line, minimal, extensible LLM inference engine built from scratch
SimpleLLM is a minimal, extensible large language model inference engine implemented in roughly 950 lines of code, built from scratch to serve both as a learning tool and a research platform for novel inference techniques. It provides the core components of an LLM runtime—such as tokenization, batching, and asynchronous execution—without the abstraction overhead of more complex engines, making it easier for developers and researchers to understand and modify. ... -
4
Nano-vLLM
A lightweight vLLM implementation built from scratch
Nano-vLLM is a lightweight implementation of the vLLM inference engine designed to run large language models efficiently while maintaining a minimal and readable codebase. The project recreates the core functionality of vLLM in a simplified architecture written in approximately a thousand lines of Python, making it easier for developers and researchers to understand how modern LLM inference systems work. -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
TokenSpeed
TokenSpeed is a speed-of-light LLM inference engine
TokenSpeed is an LLM inference engine designed for high-performance production agent workloads. It aims to combine TensorRT-LLM-level speed with vLLM-level usability, making it relevant for teams that need fast generation without sacrificing developer ergonomics. The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. -
6
Pruna AI
Pruna is a model optimization framework built for developers
Pruna is an open-source, self-hostable AI inference engine designed to help teams deploy and manage large language models (LLMs) efficiently across private or hybrid infrastructures. Built with performance and developer ergonomics in mind, Pruna simplifies inference workflows by enabling multi-model orchestration, autoscaling, GPU resource allocation, and compatibility with popular open-source models. -
7
Chitu
High-performance inference framework for large language models
Chitu is a high-performance inference engine designed to deploy and run large language models efficiently in production environments. The framework focuses on improving efficiency, flexibility, and scalability for organizations that need to run LLM inference workloads across different hardware platforms. It supports heterogeneous computing environments, including CPUs, GPUs, and various specialized AI accelerators, allowing models to run across a wide range of infrastructure configurations. ... -
8
LightLLM
LightLLM is a Python-based LLM (Large Language Model) inference
LightLLM is a high-performance inference and serving framework designed specifically for large language models, focusing on lightweight architecture, scalability, and efficient deployment. The framework enables developers to run and serve modern language models with significantly improved speed and resource efficiency compared to many traditional inference systems. Built primarily in Python, the project integrates optimization techniques and ideas from several leading open-source... -
9
SAM 3
Code for running inference and finetuning with SAM 3 model
SAM 3 (Segment Anything Model 3) is a unified foundation model for promptable segmentation in both images and videos, capable of detecting, segmenting, and tracking objects. It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
Cactus
Low-latency AI inference engine optimized for mobile devices
Cactus is a low-latency, energy-efficient AI inference framework designed specifically for mobile devices and wearables, enabling advanced machine learning capabilities directly on-device. It provides a full-stack architecture composed of an inference engine, a computation graph system, and highly optimized hardware kernels tailored for ARM-based processors. Cactus emphasizes efficient memory usage through techniques such as zero-copy computation graphs and quantized model formats, allowing large models to run within the constraints of mobile hardware. ... -
11
AI Runner
Offline inference engine for art, real-time voice conversations
AI Runner is an offline inference engine designed to run a collection of AI workloads on your own machine, including image generation for art, real-time voice conversations, LLM-powered chatbots and automated workflows. It is implemented as a desktop-oriented Python application and emphasizes privacy and self-hosting, allowing users to work with text-to-speech, speech-to-text, text-to-image and multimodal models without sending data to external services. -
12
Parallax
Parallax is a distributed model serving framework
Parallax is a decentralized inference framework designed to run large language models across distributed computing resources. Instead of relying on centralized GPU clusters in data centers, the system allows multiple heterogeneous machines to collaborate in serving AI inference workloads. Parallax divides model layers across different nodes and dynamically coordinates them to form a complete inference pipeline. A two-stage scheduling architecture determines how model layers are allocated to... -
13
HunyuanWorld-Voyager
RGBD video generation model conditioned on camera input
...The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video diffusion model with an efficient long-range world exploration engine powered by auto-regressive inference. To support training, the team built a scalable data engine that automatically curates large video datasets with camera pose estimation and metric depth prediction. As a result, Voyager delivers state-of-the-art performance on world exploration benchmarks while maintaining photometric, style, and 3D consistency. -
14
MLC LLM
Universal LLM Deployment Engine with ML Compilation
MLC LLM is a machine learning compiler and deployment framework designed to enable efficient execution of large language models across a wide range of hardware platforms. The project focuses on compiling models into optimized runtimes that can run natively on devices such as GPUs, mobile processors, browsers, and edge hardware. By leveraging machine learning compilation techniques, mlc-llm produces high-performance inference engines that maintain consistent APIs across platforms. The system... -
15
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
...It replaces full attention over all tokens with sparse selection of compressed latent memory states. Document-wise rotary position encoding and top-k routing keep training and inference close to linear complexity. A tiered KV-cache design stores routing keys on GPU while larger content states can remain on CPU. Its Memory Parallel engine distributes scoring and transfers only selected memory back to the accelerator. Memory Interleave alternates retrieval, context expansion, and generation to improve multi-hop reasoning across distant segments. ... -
16
marqo
Tensor search for humans
A tensor-based search and analytics engine that seamlessly integrates with your applications, websites, and workflows. Marqo is a versatile and robust search and analytics engine that can be integrated into any website or application. Due to horizontal scalability, Marqo provides lightning-fast query times, even with millions of documents. Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. It can seamlessly handle image-to-image, image-to-text and... -
17
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
LMCache is an extension layer for LLM serving engines that accelerates inference, especially with long contexts, by storing and reusing key-value (KV) attention caches across requests. Instead of rebuilding KV states for repeated or shared text segments, LMCache persists and retrieves them from multiple tiers—GPU memory, CPU DRAM, and local disk—then injects them into subsequent requests to reduce TTFT and increase throughput. -
18
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything
X-AnyLabeling is an open-source data annotation platform designed to streamline the process of labeling datasets for computer vision and multimodal AI applications. The software integrates an AI-powered labeling engine that allows users to generate annotations automatically with the assistance of modern vision models such as Segment Anything and various object detection frameworks. It supports labeling tasks across images and videos and enables developers to prepare training datasets for... -
19
Matrix
Multi-Agent daTa geneRation Infra and eXperimentation framework
...That design makes Matrix particularly well-suited for large-batch inference, model benchmarking, data curation, augmentation, or generation — whether for language, code, dialogue, or multimodal tasks. It supports both open-source LLMs and proprietary models (via integration with model backends), and works with containerized or sandboxed environments for safe tool execution or external code runs. -
20
Laya
Non-autoregressive System 1 decision engine
Laya is an open-source, non-autoregressive decision engine designed to answer structured questions without generating free-form text. It supports choice, score, and yes-or-no probability decisions in a single forward pass. The system works across more than 100 languages and uses a router to select an appropriate checkpoint for each request. It can run locally on CPU or GPU hardware and includes Python and TypeScript tooling. Integrations are available for HTTP, MCP, LangChain, LangGraph,... -
21
TensorRT Node for ComfyUI
Enables the best performance on NVIDIA RTX Graphics Cards
ComfyUI_TensorRT is an extension that lets ComfyUI run AI inference through NVIDIA’s TensorRT, aiming to get faster, more efficient execution on supported GPUs. It bridges the gap between ComfyUI’s flexible, node-based workflows and TensorRT’s highly optimized engine format. The result is that complex diffusion or image-processing graphs can be accelerated without the user having to rewrite the pipeline. -
22
Superduper
Superduper: Integrate AI models and machine learning workflows
Superduper is a Python-based framework for building end-2-end AI-data workflows and applications on your own data, integrating with major databases. It supports the latest technologies and techniques, including LLMs, vector-search, RAG, and multimodality as well as classical AI and ML paradigms. Developers may leverage Superduper by building compositional and declarative objects that out-source the details of deployment, orchestration versioning, and more to the Superduper engine. This... -
23
FlexLLMGen
Running large language models on a single GPU
FlexLLMGen is an open-source inference engine designed to run large language models efficiently on limited hardware resources such as a single GPU. The system focuses on high-throughput generation workloads where large batches of text must be processed quickly, such as large-scale data extraction or document analysis tasks. Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. ... -
24
llama2.c
Inference Llama 2 in one file of pure C
llama2.c is a minimalist implementation of the Llama 2 language model architecture designed to run entirely in pure C. Created by Andrej Karpathy, this project offers an educational and lightweight framework for performing inference on small Llama 2 models without external dependencies. It provides a full training and inference pipeline: models can be trained in PyTorch and later executed using a concise 700-line C program (run.c). While it can technically load Meta’s official Llama 2... -
25
Lightning Bolts
Toolbox of models, callbacks, and datasets for AI/ML researchers
Bolts package provides a variety of components to extend PyTorch Lightning, such as callbacks & datasets, for applied research and production. Torch ORT converts your model into an optimized ONNX graph, speeding up training & inference when using NVIDIA or AMD GPUs. We can introduce sparsity during fine-tuning with SparseML, which ultimately allows us to leverage the DeepSparse engine to see performance improvements at inference time.
