AI Model2018
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.
AI Model2018
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.
AI Infra2018
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.
AI Infra2018
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.
AI Deploy2019
Turns Python ML code into production inference APIs that scale on Kubernetes or any cloud. Bundles models, dependencies, and serving logic into versioned "Bentos" with autoscaling, scale-to-zero, and multi-GPU serving for LLMs and custom models.
AI Image2019
Bundles hundreds of pretrained image backbones — ResNet, EfficientNet, ViT, ConvNeXt, Swin and more — behind one consistent API for classification and feature extraction, with training and inference scripts that reproduce published ImageNet results.
AI Audio2019
Provides a toolkit and codebase for building, training, and deploying speech and multimodal models — Automatic Speech Recognition, Text-to-Speech, and speech-aware LLMs — with modular neural components and pre-trained checkpoints for PyTorch. Supports streaming/low-latency inference, multi-language models, and optional compiled kernels for acceleration.
AI Infra2019
Runs approximate nearest-neighbor search over billions of vector embeddings, separating compute from storage so reads and writes scale independently. Offers HNSW, IVF, DiskANN, and GPU CAGRA indexes plus hybrid dense+sparse and BM25 retrieval.
AI Infra2020
Optimizes distributed PyTorch training and inference for very large models with ZeRO memory partitioning, parallelism, MoE, offload, and compression. Best when GPU memory, training cost, or cluster throughput is the bottleneck.
AI Audio2020
Extracts vocals and instrumentals from audio using an ensemble of models — MDX-Net/MDX23C, Demucs v3/v4, and the VR architecture. Runs locally via a Tkinter GUI with GPU acceleration across Nvidia, AMD, Intel, and Apple chips.
AI Infra2020
Sits between PyTorch and micrograd: eager tensors with autograd plus a small, fully hackable compiler that fuses operations into kernels. Adding a new accelerator backend takes about 25 low-level ops, so it runs on CUDA, Metal, AMD, and WebGPU.