HSTU Generative Recommenders on Triton#
Hierarchical Sequential Transduction Units (HSTU) power Generative Recommenders (GRs): recommendation workloads reformulated as generative modeling over high-cardinality, non-stationary event streams. HSTU supports both retrieval and ranking style tasks.
Triton Inference Server can serve HSTU models through the
PyTorch backend
using ahead-of-time (AOT) Inductor packages (platform: "torch_aoti"). Training,
export, KV-cache runtime, and end-to-end examples live in NVIDIA’s
recsys-examples repository rather
than in this tutorials tree.
Where to go next#
Resource |
Description |
|---|---|
Architecture, training, and inference entry points |
|
Inference features, KV-cache, AOTInductor export, and KuaiRand examples |
|
|
[!NOTE] Use the recsys-examples guides for building, exporting, and validating HSTU models. This page only points Triton users at that workflow and the Torch AOTI serving path.