Discover the Best AI Resources

Triton Inference Server

Serves machine learning and deep learning models for cloud, data center, edge and embedded environments. Supports multiple frameworks and backends, dynamic and sequence batching, HTTP/gRPC APIs, Docker deployment and NVIDIA-optimized runtimes.

Dive into Deep Learning (d2l-en)

Notebook-first deep learning textbook that teaches concepts through runnable multi-framework code, math, and exercises. Includes lecture-ready notebooks, community contributions, and broad university adoption—designed for hands-on learners and instructors.

Pre-trains a deep bidirectional Transformer encoder with masked-language-modeling and next-sentence prediction, then fine-tunes one model on 11 NLP tasks, reaching state-of-the-art on GLUE, SQuAD, and MultiNLI with little task-specific tuning.

OpenVINO

Converts, quantizes, and runs deep learning models from PyTorch, TensorFlow, ONNX, and PaddlePaddle across Intel CPUs, GPUs, and NPUs without the training framework. Adds a GenAI pipeline for LLMs plus Hugging Face, vLLM, and LangChain integrations.

JAX

Provides composable function transformations for Python+NumPy—automatic differentiation, JIT compilation, and vectorization—while using XLA to run and scale numerical programs on GPUs/TPUs for ML and scientific computing.

Transformers

Provides unified model definitions and a single API for pretrained text, vision, audio, and multimodal models for both training and inference. Emphasizes cross-framework compatibility (PyTorch/TF/JAX), pipeline-based inference, and direct access to 1M+ Hub checkpoints.

Hugging Face — Transformers

Turns model definitions into a shared layer across training and inference stacks, covering text, vision, audio, video, and multimodal models. Pipelines, Trainer, and generation APIs make pretrained models usable without locking teams to one framework.

PennyLane

Differentiable programming framework for quantum computers: build variational circuits, compute their gradients alongside PyTorch, TensorFlow, or JAX, and run identical code on simulators or real hardware via IBM, AWS Braket, and Google plugins.

Chops any layer-sequence model across accelerators and splits each mini-batch into micro-batches to keep the pipeline busy, hitting near-linear speedup without architecture-specific tricks or fast interconnects.

JAX: High performance array computing — JAX documentation

Turns NumPy-style Python into differentiable, compiled, vectorized programs for CPU, GPU, and TPU. Its leverage is composable transformations: grad, jit, vmap, and sharding combine instead of living in separate APIs.

ONNX Runtime | Home

Runs ONNX models faster on CPU, GPU, and NPU by routing graph subgraphs to backend execution providers (CUDA, TensorRT, OpenVINO, DirectML, CoreML). One engine serves the same model across cloud, browser, mobile, and edge, for both inference and training.

MLRun

Turns plain Python functions into versioned, serverless ML jobs that run unchanged locally or on Kubernetes, with built-in tracking and deployment. Its feature store derives both offline (batch) and online (real-time) serving from one definition.