Open Source LLM Inference Tools - Page 4
Sort By:
LLM Inference Tools
View 133 business solutions-
Gen AI apps are built with MongoDB AtlasMongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
-
Time tracking software for the global workforceIt's easy with Hubstaff, a time-tracking and workforce management platform that automates almost every aspect of running or growing a business. Teams can track time to projects and to-dos using Hubstaff's desktop, web, or mobile applications. You'll be able to see how much time your team spends on different tasks, plus productivity metrics like activity rates and app usage through Hubstaff's online dashboard. Most of the available features are customizable on a per-user basis, so you can create the team management tool you need.
-
1
Arch Gateway
The AI-native (edge and LLM) proxy for agents
Arch is an AI-native proxy designed to facilitate the development of agentic applications by handling complex tasks such as input clarification, agent routing, and seamless integration of prompts with tools for common tasks. It provides unified access and observability of Large Language Models (LLMs), enabling developers to build applications more efficiently. Arch supports both edge and LLM deployments, offering flexibility in various environments. -
2
CTranslate2
Fast inference engine for Transformer models
CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). The project supports x86-64 and AArch64/ARM64 processors and integrates multiple backends that are optimized for these platforms: Intel MKL, oneDNN, OpenBLAS, Ruy, and Apple Accelerate. -
3
ChatLLM.cpp
Pure C++ implementation of several models for real-time chatting
chatllm.cpp is a pure C++ implementation designed for real-time chatting with Large Language Models (LLMs) on personal computers, supporting both CPU and GPU executions. It enables users to run various LLMs ranging from less than 1 billion to over 300 billion parameters, facilitating responsive and efficient conversational AI experiences without relying on external servers. -
4
DeepDetect
Deep Learning API and Server in C++14 support for Caffe, PyTorch
The core idea is to remove the error sources and difficulties of Deep Learning applications by providing a safe haven of commoditized practices, all available as a single core. While the Open Source Deep Learning Server is the core element, with REST API, and multi-platform support that allows training & inference everywhere, the Deep Learning Platform allows higher level management for training neural network models and using them as if they were simple code snippets. Ready for applications of image tagging, object detection, segmentation, OCR, Audio, Video, Text classification, CSV for tabular data and time series. Neural network templates for the most effective architectures for GPU, CPU, and Embedded devices. Training in a few hours and with small data thanks to 25+ pre-trained models. Full Open Source, with an ecosystem of tools (API clients, video, annotation, ...) Fast Server written in pure C++, a single codebase for Cloud, Desktop & Embedded. -
Accounting Software Built for Owners, and Their ClientsBalancing your books, client relationships, and business isn’t easy. FreshBooks gives you the info and time you need to focus on your big picture—your business, team, and clients.
-
5
DeepSparse
Sparsity-aware deep learning inference runtime for CPUs
A sparsity-aware enterprise inferencing system for AI models on CPUs. Maximize your CPU infrastructure with DeepSparse to run performant computer vision (CV), natural language processing (NLP), and large language models (LLMs). -
6
Distributed Llama
Connect home devices into a powerful cluster to accelerate LLM
Distributed Llama is an open-source project that enables users to connect multiple home devices into a powerful cluster to accelerate Large Language Model (LLM) inference. By leveraging tensor parallelism and high-speed synchronization over Ethernet, it allows for faster performance as more devices are added to the cluster. The system supports various operating systems, including Linux, macOS, and Windows, and is optimized for both ARM and x86_64 AVX2 CPUs. -
7
EconML
Python Package for ML-Based Heterogeneous Treatment Effects Estimation
EconML is a Python package for estimating heterogeneous treatment effects from observational data via machine learning. This package was designed and built as part of the ALICE project at Microsoft Research with the goal of combining state-of-the-art machine learning techniques with econometrics to bring automation to complex causal inference problems. One of the biggest promises of machine learning is to automate decision-making in a multitude of domains. At the core of many data-driven personalized decision scenarios is the estimation of heterogeneous treatment effects: what is the causal effect of an intervention on an outcome of interest for a sample with a particular set of features? In a nutshell, this toolkit is designed to measure the causal effect of some treatment variable(s) T on an outcome variable Y, controlling for a set of features X, W and how does that effect vary as a function of X. -
8
GPT-NeoX
Implementation of model parallel autoregressive transformers on GPUs
This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training. For those looking for a TPU-centric codebase, we recommend Mesh Transformer JAX. If you are not looking to train models with billions of parameters from scratch, this is likely the wrong library to use. For generic inference needs, we recommend you use the Hugging Face transformers library instead which supports GPT-NeoX models. -
9
LazyLLM
Easiest and laziest way for building multi-agent LLMs applications
LazyLLM is an optimized, lightweight LLM server designed for easy and fast deployment of large language models. It is fully compatible with the OpenAI API specification, enabling developers to integrate their own models into applications that normally rely on OpenAI’s endpoints. LazyLLM emphasizes low resource usage and fast inference while supporting multiple models. -
Instant Remote Support Software. Unattended Remote Access Software.Zoho Assist is cloud-based remote support and remote access software that helps you support customers from a distance through web-based, on-demand remote support sessions. Set up unattended remote access and manage remote PCs, laptops, mobile devices, and servers effortlessly. A few seconds is all you need to establish secure connections to offer your customers remote support solutions.
-
10
OpenVINO Model Server
A scalable inference server for models optimized with OpenVINO
OpenVINO™ Model Server is a high-performance inference serving system designed to host and serve machine learning models that have been optimized with the OpenVINO toolkit. It’s implemented in C++ for scalability and efficiency, making it suitable for both edge and cloud deployments where inference workloads must be reliable and high throughput. The server exposes model inference via standard network protocols like REST and gRPC, allowing any client that speaks those protocols to request predictions remotely, abstracting away the complexity of where and how the model runs. It supports model deployment in diverse environments including Docker, bare-metal machines, and Kubernetes clusters, and is especially useful in microservices architectures where AI services need to scale independently. The system supports a wide range of model sources, letting you host models from local storage, remote object storage, or even pull from model hubs. -
11
PEFT
State-of-the-art Parameter-Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's parameters. Fine-tuning large-scale PLMs is often prohibitively costly. In this regard, PEFT methods only fine-tune a small number of (extra) model parameters, thereby greatly decreasing the computational and storage costs. Recent State-of-the-Art PEFT techniques achieve performance comparable to that of full fine-tuning. -
12
RWKV Runner
A RWKV management and startup tool, full automation, only 8MB
RWKV (pronounced as RwaKuv) is an RNN with GPT-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free. Default configs has enabled custom CUDA kernel acceleration, which is much faster and consumes much less VRAM. If you encounter possible compatibility issues, go to the Configs page and turn off Use Custom CUDA kernel to Accelerate. -
13
SAHI
A lightweight vision library for performing large object detection
A lightweight vision library for performing large-scale object detection & instance segmentation. Object detection and instance segmentation are by far the most important fields of applications in Computer Vision. However, detection of small objects and inference on large images are still major issues in practical usage. Here comes the SAHI to help developers overcome these real-world problems with many vision utilities. Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. -
14
Scanpy
Single-cell analysis in Python
Scanpy is a scalable toolkit for analyzing single-cell gene expression data built jointly with anndata. It includes preprocessing, visualization, clustering, trajectory inference and differential expression testing. The Python-based implementation efficiently deals with datasets of more than one million cells. -
15
TNN
Uniform deep learning inference framework for mobile
TNN, a high-performance, lightweight neural network inference framework open sourced by Tencent Youtu Lab. It also has many outstanding advantages such as cross-platform, high performance, model compression, and code tailoring. The TNN framework further strengthens the support and performance optimization of mobile devices on the basis of the original Rapidnet and ncnn frameworks. At the same time, it refers to the high performance and good scalability characteristics of the industry's mainstream open source frameworks, and expands the support for X86 and NV GPUs. On the mobile phone, TNN has been used by many applications such as mobile QQ, weishi, and Pitu. As a basic acceleration framework for Tencent Cloud AI, TNN has provided acceleration support for the implementation of many businesses. Everyone is welcome to participate in the collaborative construction to promote the further improvement of the TNN inference framework. -
16
TorchAudio
Data manipulation and transformation for audio signal processing
The aim of torchaudio is to apply PyTorch to the audio domain. By supporting PyTorch, torchaudio follows the same philosophy of providing strong GPU acceleration, having a focus on trainable features through the autograd system, and having consistent style (tensor names and dimension names). Therefore, it is primarily a machine learning library and not a general signal processing library. The benefits of PyTorch can be seen in torchaudio through having all the computations be through PyTorch operations which makes it easy to use and feel like a natural extension. -
17
TorchRec
Pytorch domain library for recommendation systems
TorchRec is a PyTorch domain library built to provide common sparsity & parallelism primitives needed for large-scale recommender systems (RecSys). It allows authors to train models with large embedding tables sharded across many GPUs. Parallelism primitives that enable easy authoring of large, performant multi-device/multi-node models using hybrid data-parallelism/model-parallelism. The TorchRec sharder can shard embedding tables with different sharding strategies including data-parallel, table-wise, row-wise, table-wise-row-wise, and column-wise sharding. The TorchRec planner can automatically generate optimized sharding plans for models. Pipelined training overlaps dataloading device transfer (copy to GPU), inter-device communications (input_dist), and computation (forward, backward) for increased performance. Optimized kernels for RecSys powered by FBGEMM. Quantization support for reduced precision training and inference. Common modules for RecSys. -
18
towhee
Framework that is dedicated to making neural data processing
Towhee is an open-source machine-learning pipeline that helps you encode your unstructured data into embeddings. You can use our Python API to build a prototype of your pipeline and use Towhee to automatically optimize it for production-ready environments. From images to text to 3D molecular structures, Towhee supports data transformation for nearly 20 different unstructured data modalities. We provide end-to-end pipeline optimizations, covering everything from data decoding/encoding, to model inference, making your pipeline execution 10x faster. Towhee provides out-of-the-box integration with your favorite libraries, tools, and frameworks, making development quick and easy. Towhee includes a pythonic method-chaining API for describing custom data processing pipelines. We also support schemas, making processing unstructured data as easy as handling tabular data. -
19
AI Chatbots based on GPT Architecture
Training & Implementation of chatbots leveraging GPT-like architecture
Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations. It sure seems like there are a lot of text-generation chatbots out there, but it's hard to find a python package or model that is easy to tune around a simple text file of message data. This repo is a simple attempt to help solve that problem. ai-msgbot covers the practical use case of building a chatbot that sounds like you (or some dataset/persona you choose) by training a text-generation model to generate conversation in a consistent structure. This structure is then leveraged to deploy a chatbot that is a "free-form" model that consistently replies like a human. Some of the trained models can be interacted with through the HuggingFace spaces and model inference APIs on the ETHZ Analytics Organization page on huggingface.co. -
20
AIMET
AIMET is a library that provides advanced quantization and compression
Qualcomm Innovation Center (QuIC) is at the forefront of enabling low-power inference at the edge through its pioneering model-efficiency research. QuIC has a mission to help migrate the ecosystem toward fixed-point inference. With this goal, QuIC presents the AI Model Efficiency Toolkit (AIMET) - a library that provides advanced quantization and compression techniques for trained neural network models. AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed. -
21
Arize Phoenix
Uncover insights, surface problems, monitor, and fine tune your LLM
Phoenix provides ML insights at lightning speed with zero-config observability for model drift, performance, and data quality. Phoenix is an Open Source ML Observability library designed for the Notebook. The toolset is designed to ingest model inference data for LLMs, CV, NLP and tabular datasets. It allows Data Scientists to quickly visualize their model data, monitor performance, track down issues & insights, and easily export to improve. Deep Learning Models (CV, LLM, and Generative) are an amazing technology that will power many of future ML use cases. A large set of these technologies are being deployed into businesses (the real world) in what we consider a production setting. -
22
BentoML
Unified Model Serving Framework
BentoML simplifies ML model deployment and serves your models at a production scale. Support multiple ML frameworks natively: Tensorflow, PyTorch, XGBoost, Scikit-Learn and many more! Define custom serving pipeline with pre-processing, post-processing and ensemble models. Standard .bento format for packaging code, models and dependencies for easy versioning and deployment. Integrate with any training pipeline or ML experimentation platform. Parallelize compute-intense model inference workloads to scale separately from the serving logic. Adaptive batching dynamically groups inference requests for optimal performance. Orchestrate distributed inference graph with multiple models via Yatai on Kubernetes. Easily configure CUDA dependencies for running inference with GPU. Automatically generate docker images for production deployment. -
23
DeepSpeed
Deep learning optimization library: makes distributed training easy
DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for Deep Learning Training and Inference. With DeepSpeed you can: 1. Train/Inference dense or sparse models with billions or trillions of parameters 2. Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. These innovations such as ZeRO, 3D-Parallelism, DeepSpeed-MoE, ZeRO-Infinity, etc. fall under the training pillar. -
24
Eko
Build Production-ready Agentic Workflow with Natural Language
Eko (Eko Keeps Operating) is a JavaScript framework designed for building production-ready agent-based workflows using natural language commands. It allows developers to create automated agents that can handle complex workflows in both computer and browser environments. With a focus on high development efficiency, Eko simplifies the creation of multi-step workflows, enabling users to integrate and automate tasks across platforms. It provides a unified interface for managing agents, offering features such as web resource access and high task complexity handling. Eko is open-source and can be used to execute tasks like browser automation, system operations, and software testing. -
25
Embedding Studio
Framework which allows you transform your Vector Database
Embedding Studio is a framework that transforms vector databases into feature-rich search engines. It leverages embeddings to enhance search capabilities, enabling more accurate and context-aware retrieval of information. Embedding Studio supports various data types and integrates seamlessly with existing databases, providing tools for fine-tuning and optimizing embeddings to suit specific application needs.