Open Source Python LLM Inference Tools - Page 4
Sort By:
Python LLM Inference Tools
View 137 business solutionsBrowse free open source Python LLM Inference Tools and projects below. Use the toggles on the left to filter open source Python LLM Inference Tools by OS, license, language, programming language, and project status.
-
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
Pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming
A pytorch-toolbelt is a Python library with a set of bells and whistles for PyTorch for fast R&D prototyping and Kaggle farming. Easy model building using flexible encoder-decoder architecture. Modules: CoordConv, SCSE, Hypercolumn, Depthwise separable convolution and more. GPU-friendly test-time augmentation TTA for segmentation and classification. GPU-friendly inference on huge (5000x5000) images. Every-day common routines (fix/restore random seed, filesystem utils, metrics). Losses: BinaryFocalLoss, Focal, ReducedFocal, Lovasz, Jaccard and Dice losses, Wing Loss and more. Extras for Catalyst library (Visualization of batch predictions, additional metrics). By design, both encoder and decoder produces a list of tensors, from fine (high-resolution, indexed 0) to coarse (low-resolution) feature maps. Access to all intermediate feature maps is beneficial if you want to apply deep supervision losses on them or encoder-decoder of object detection task. -
2
RamaLama
Simplifies the local serving of AI models from any source
RamaLama is an open-source developer tool that simplifies working with and serving AI models locally or in production by leveraging container technologies like Docker, Podman, and OCI registries, allowing AI inference workflows to be treated like standard container deployments. It abstracts away much of the complexity of configuring AI runtimes, dependencies, and hardware optimizations by detecting available GPUs (or falling back to CPU) and automatically pulling a container image pre-configured for the detected hardware environment. Developers can use familiar container commands to pull, run, and interact with AI models from any source, treating models similarly to how container images are handled in OCI workflows. RamaLama supports multiple model registries and offers a REST API or chatbot interface for interacting with running models, making it flexible for local development, testing, or integration into larger systems. -
3
Ray
A unified framework for scalable computing
Modern workloads like deep learning and hyperparameter tuning are compute-intensive and require distributed or parallel execution. Ray makes it effortless to parallelize single machine code — go from a single CPU to multi-core, multi-GPU or multi-node with minimal code changes. Accelerate your PyTorch and Tensorflow workload with a more resource-efficient and flexible distributed execution framework powered by Ray. Accelerate your hyperparameter search workloads with Ray Tune. Find the best model and reduce training costs by using the latest optimization algorithms. Deploy your machine learning models at scale with Ray Serve, a Python-first and framework agnostic model serving framework. Scale reinforcement learning (RL) with RLlib, a framework-agnostic RL library that ships with 30+ cutting-edge RL algorithms including A3C, DQN, and PPO. Easily build out scalable, distributed systems in Python with simple and composable primitives in Ray Core. -
4
Repo of Tree of Thoughts (ToT)
Implementation of "Tree of Thoughts
Language models are increasingly being deployed for general problem-solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem-solving. ToT allows LMs to perform deliberate decision-making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices. -
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
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. -
6
SSD in PyTorch 1.0
High quality, fast, modular reference implementation of SSD in PyTorch
This repository implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd.pytorch, pytorch-ssd and maskrcnn-benchmark. This repository aims to be the code base for research based on SSD. Multi-GPU training and inference: We use DistributedDataParallel, you can train or test with arbitrary GPU(s), the training schema will change accordingly. Add your own modules without pain. We abstract backbone, Detector, BoxHead, BoxPredictor, etc. You can replace every component with your own code without changing the code base. For example, You can add EfficientNet as the backbone, just add efficient_net.py (ALREADY ADDED) and register it, specific it in the config file, It's done! Smooth and enjoyable training procedure: we save the state of model, optimizer, scheduler, training iter, you can stop your training and resume training exactly from the save point without change your training CMD. -
7
SageMaker Hugging Face Inference Toolkit
Library for serving Transformers models on Amazon SageMaker
SageMaker Hugging Face Inference Toolkit is an open-source library for serving Transformers models on Amazon SageMaker. This library provides default pre-processing, predict and postprocessing for certain Transformers models and tasks. It utilizes the SageMaker Inference Toolkit for starting up the model server, which is responsible for handling inference requests. For the Dockerfiles used for building SageMaker Hugging Face Containers, see AWS Deep Learning Containers. The SageMaker Hugging Face Inference Toolkit implements various additional environment variables to simplify your deployment experience. The Hugging Face Inference Toolkit allows user to override the default methods of the HuggingFaceHandlerService. SageMaker Hugging Face Inference Toolkit is licensed under the Apache 2.0 License. -
8
SageMaker Inference Toolkit
Serve machine learning models within a Docker container
Serve machine learning models within a Docker container using Amazon SageMaker. Amazon SageMaker is a fully managed service for data science and machine learning (ML) workflows. You can use Amazon SageMaker to simplify the process of building, training, and deploying ML models. Once you have a trained model, you can include it in a Docker container that runs your inference code. A container provides an effectively isolated environment, ensuring a consistent runtime regardless of where the container is deployed. Containerizing your model and code enables fast and reliable deployment of your model. The SageMaker Inference Toolkit implements a model serving stack and can be easily added to any Docker container, making it deployable to SageMaker. This library's serving stack is built on Multi Model Server, and it can serve your own models or those you trained on SageMaker using machine learning frameworks with native SageMaker support. -
9
SageMaker MXNet Inference Toolkit
Toolkit for allowing inference and serving with MXNet in SageMaker
SageMaker MXNet Inference Toolkit is an open-source library for serving MXNet models on Amazon SageMaker. This library provides default pre-processing, predict and postprocessing for certain MXNet model types and utilizes the SageMaker Inference Toolkit for starting up the model server, which is responsible for handling inference requests. AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet. Deep Learning Containers provide optimized environments with TensorFlow and MXNet, Nvidia CUDA (for GPU instances), and Intel MKL (for CPU instances) libraries and are available in the Amazon Elastic Container Registry (Amazon ECR). The AWS DLCs are used in Amazon SageMaker as the default vehicles for your SageMaker jobs such as training, inference, transforms etc. They've been tested for machine learning workloads on Amazon EC2, Amazon ECS and Amazon EKS services as well. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
10
Seldon Core
An MLOps framework to package, deploy, monitor and manage models
The de facto standard open-source platform for rapidly deploying machine learning models on Kubernetes. Seldon Core, our open-source framework, makes it easier and faster to deploy your machine learning models and experiments at scale on Kubernetes. Seldon Core serves models built in any open-source or commercial model building framework. You can make use of powerful Kubernetes features like custom resource definitions to manage model graphs. And then connect your continuous integration and deployment (CI/CD) tools to scale and update your deployment. Built on Kubernetes, runs on any cloud and on-premises. Framework agnostic, supports top ML libraries, toolkits and languages. Advanced deployments with experiments, ensembles and transformers. Our open-source framework makes it easier and faster to deploy your machine learning models and experiments at scale on Kubernetes. The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes. -
11
SetFit
Efficient few-shot learning with Sentence Transformers
SetFit is an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers. It achieves high accuracy with little labeled data - for instance, with only 8 labeled examples per class on the Customer Reviews sentiment dataset, SetFit is competitive with fine-tuning RoBERTa Large on the full training set of 3k examples. -
12
Sockeye
Sequence-to-sequence framework, focused on Neural Machine Translation
Sockeye is an open-source sequence-to-sequence framework for Neural Machine Translation built on PyTorch. It implements distributed training and optimized inference for state-of-the-art models, powering Amazon Translate and other MT applications. For a quickstart guide to training a standard NMT model on any size of data, see the WMT 2014 English-German tutorial. If you are interested in collaborating or have any questions, please submit a pull request or issue. You can also send questions to sockeye-dev-at-amazon-dot-com. Developers may be interested in our developer guidelines. Starting with version 3.0.0, Sockeye is also based on PyTorch. We maintain backwards compatibility with MXNet models of version 2.3.x with 3.0.x. If MXNet 2.x is installed, Sockeye can run both with PyTorch or MXNet. All models trained with 2.3.x (using MXNet) can be converted to models running with PyTorch using the converter CLI (sockeye.mx_to_pt). -
13
SparseML
Libraries for applying sparsification recipes to neural networks
SparseML is an optimization toolkit for training and deploying deep learning models using sparsification techniques like pruning and quantization to improve efficiency. -
14
SuperDuperDB
Integrate, train and manage any AI models and APIs with your database
Build and manage AI applications easily without needing to move your data to complex pipelines and specialized vector databases. Integrate AI and vector search directly with your database including real-time inference and model training. Just using Python. A single scalable deployment of all your AI models and APIs which is automatically kept up-to-date as new data is processed immediately. No need to introduce an additional database and duplicate your data to use vector search and build on top of it. SuperDuperDB enables vector search in your existing database. Integrate and combine models from Sklearn, PyTorch, HuggingFace with AI APIs such as OpenAI to build even the most complex AI applications and workflows. Train models on your data in your datastore simply by querying without additional ingestion and pre-processing. -
15
TalkingHeads
A library to communicate with ChatGPT, Claude, Copilot, Gemini
TalkingHeads is a Python library designed to facilitate communication with various AI chat agents, including ChatGPT, Claude, Copilot, Gemini, HuggingChat, and Pi. It provides a unified interface for interacting with these platforms, simplifying the integration of conversational AI capabilities into applications. TalkingHeads supports browser automation and offers tools to manage sessions, handle prompts, and process responses effectively. -
16
TensorFlow Model Optimization Toolkit
A toolkit to optimize ML models for deployment for Keras & TensorFlow
The TensorFlow Model Optimization Toolkit is a suite of tools for optimizing ML models for deployment and execution. Among many uses, the toolkit supports techniques used to reduce latency and inference costs for cloud and edge devices (e.g. mobile, IoT). Deploy models to edge devices with restrictions on processing, memory, power consumption, network usage, and model storage space. Enable execution on and optimize for existing hardware or new special purpose accelerators. Choose the model and optimization tool depending on your task. In many cases, pre-optimized models can improve the efficiency of your application. Try the post-training tools to optimize an already-trained TensorFlow model. Use training-time optimization tools and learn about the techniques. -
17
TensorFlow Probability
Probabilistic reasoning and statistical analysis in TensorFlow
TensorFlow Probability is a library for probabilistic reasoning and statistical analysis. TensorFlow Probability (TFP) is a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware (TPU, GPU). It's for data scientists, statisticians, ML researchers, and practitioners who want to encode domain knowledge to understand data and make predictions. Since TFP inherits the benefits of TensorFlow, you can build, fit, and deploy a model using a single language throughout the lifecycle of model exploration and production. TFP is open source and available on GitHub. Tools to build deep probabilistic models, including probabilistic layers and a `JointDistribution` abstraction. Variational inference and Markov chain Monte Carlo. A wide selection of probability distributions and bijectors. Optimizers such as Nelder-Mead, BFGS, and SGLD. -
18
Text Generation Inference
Large Language Model Text Generation Inference
Text Generation Inference is a high-performance inference server for text generation models, optimized for Hugging Face's Transformers. It is designed to serve large language models efficiently with optimizations for performance and scalability. -
19
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. -
20
UForm
Multi-Modal Neural Networks for Semantic Search, based on Mid-Fusion
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space! It comes with a set of homonymous pre-trained networks available on HuggingFace portal and extends the transfromers package to support Mid-fusion Models. Late-fusion models encode each modality independently, but into one shared vector space. Due to independent encoding late-fusion models are good at capturing coarse-grained features but often neglect fine-grained ones. This type of models is well-suited for retrieval in large collections. The most famous example of such models is CLIP by OpenAI. Early-fusion models encode both modalities jointly so they can take into account fine-grained features. Usually, these models are used for re-ranking relatively small retrieval results. Mid-fusion models are the golden midpoint between the previous two types. Mid-fusion models consist of two parts – unimodal and multimodal. -
21
dstack
Open-source tool designed to enhance the efficiency of workloads
dstack is an open-source tool designed to enhance the efficiency of running ML workloads in any cloud (AWS, GCP, Azure, Lambda, etc). It streamlines development and deployment, reduces cloud costs, and frees users from vendor lock-in. -
22
llama2-webui
Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere
Running Llama 2 with gradio web UI on GPU or CPU from anywhere (Linux/Windows/Mac). -
23
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 text-to-image search and analytics. Marqo adapts and stores your data in a fully schemaless manner. It combines tensor search with a query DSL that provides efficient pre-filtering. Tensor search allows you to go beyond keyword matching and search based on the meaning of text, images and other unstructured data. Be a part of the tribe and help us revolutionize the future of search. Whether you are a contributor, a user, or simply have questions about Marqo, we got your back. -
24
pipeless
A computer vision framework to create and deploy apps in minutes
Pipeless is an open-source computer vision framework to create and deploy applications without the complexity of building and maintaining multimedia pipelines. It ships everything you need to create and deploy efficient computer vision applications that work in real-time in just minutes. Pipeless is inspired by modern serverless technologies. It provides the development experience of serverless frameworks applied to computer vision. You provide some functions that are executed for new video frames and Pipeless takes care of everything else. You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. You can deploy your Pipeless application with a single command to edge and IoT devices or the cloud. -
25
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.
