---
title: "Portable Paged Attention in Helion – PyTorch"
url: https://daily.dev/posts/portable-paged-attention-in-helion-pytorch-p3relozri
source_url: https://pytorch.org/blog/portable-paged-attention-in-helion/
type: article
source: "PyTorch"
published: 2026-02-03T17:34:48.536Z
updated: 2026-02-03T17:35:14.159Z
tags: ["performance", "llm", "gpu", "pytorch"]
reading_time: 25
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Portable Paged Attention in Helion – PyTorch

**[PyTorch](https://daily.dev/sources/pytorch)** · 25 min read · 0 upvotes · 0 comments

## Summary

IBM Research implemented paged attention (the core kernel of vLLM) in Helion, PyTorch's new domain-specific language for portable high-performance kernels. The Helion implementation required 133 lines versus 295 in Triton, with automatic handling of tiling, masking, and boundaries. On NVIDIA H100, the Helion kernel matched or exceeded Triton performance for decode workloads (132-153% of Triton speed) and was competitive for prefill. End-to-end vLLM benchmarks showed dynamic shapes achieved 96% of Triton throughput on H100, while static shapes caused severe JIT overhead. The team found Helion's autotuner powerful but time-consuming (10 hours for quick mode), and concluded that dynamic shapes are essential for production inference servers with diverse request patterns.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://pytorch.org/blog/portable-paged-attention-in-helion/>

## Similar posts on daily.dev

- [Portable vLLM Model Inference Kernels in Helion – PyTorch](https://daily.dev/posts/portable-vllm-model-inference-kernels-in-helion-pytorch-ay8n7jjmi) · PyTorch · 0 upvotes · 0 comments
- [Helion on TPU: Towards Hardware Heterogeneous Kernel Authoring – PyTorch](https://daily.dev/posts/helion-on-tpu-towards-hardware-heterogeneous-kernel-authoring-pytorch-uvlidlhmw) · PyTorch · 1 upvotes · 0 comments
- [Helion: A High-Level DSL for Performant and Portable ML Kernels – PyTorch](https://daily.dev/posts/helion-a-high-level-dsl-for-performant-and-portable-ml-kernels-pytorch-przi31los) · PyTorch · 0 upvotes · 0 comments

---

Tags: [#performance](https://daily.dev/tags/performance), [#llm](https://daily.dev/tags/llm), [#gpu](https://daily.dev/tags/gpu), [#pytorch](https://daily.dev/tags/pytorch)

[View this post on daily.dev](https://daily.dev/posts/portable-paged-attention-in-helion-pytorch-p3relozri)