Results for “inference infrastructure”

22 tools in the directory · Updated 2 Nov 2026

“inference infrastructure”Download or installWays to use: SDK / libraryShowing 22 tools

Roboflow Inferenceby RoboflowYC S20Self-hosted computer vision inference server with WorkflowsFree
LMCacheby LMCacheOpen-source KV-cache infrastructure for storing and reusing LLM inference cache.Free
vLLMby vLLMLLM inference and serving library.Free
PyTorchby PyTorch FoundationOpen source machine learning framework for building and training deep learning modelsFree
LLM Compressorby IBMOpen-source Python library for quantizing and pruning LLMs to run faster in vLLMFree
OpenVINOby IntelOpen source AI inference toolkit for deploying models across Intel hardwareFree
Transformersby Hugging FaceOpen-source Python library defining state-of-the-art ML models for inference and trainingFree
Rayby AnyscaleOpen-source Python framework for scaling AI and ML workloadsFree
Ollamaby OllamaYC W21Run and build with open AI models locally or in the cloudFreemium
Strands Agentsby AmazonOpen source toolkit for building AI agent harnesses in Python and TypeScriptFree
FastEmbedby QdrantLightweight Python library for generating text, sparse, image and reranking embeddingsFree
mlpackby mlpackOpen-source C++ machine-learning library with Python, Julia, R, Go and command-line interfaces.Free
Guardrails AIby Guardrails AIValidate model inputs and outputs with reusable Python guardsContact sales
Pydantic AIby PydanticOpen source Python framework for typed AI agents with validation and durable runsFreemium
Milvusby ZillizOpen-source vector database for large-scale AI search and retrievalFreemium
smolagentsby Hugging FaceOpen-source Python library for building agents that write their actions as codeFree
Griptapeby GriptapePython framework for AI agents, retrieval and structured workflows.Unknown
Cogneeby CogneeOpen-source memory engine for AI agents, with a hosted option.Freemium
AgileRLby AgileRLOpen-source Python library for reinforcement learning and language-model post-training.Contact sales
LiteLLMby LiteLLMYC W23Open-source AI gateway that puts many LLM providers behind one API with spend caps and routingFreemium
LIBSVMby LibSVMLIBSVM is a software library and command-line toolkit for support vector classification, regression, and one-class estimation.Free
Instructorby InstructorA developer library for extracting structured, validated data from language models.Unknown