PulseAugur
中
实时 03:20:47
English(EN) Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0

新的INT8内核加速消费级GPU上的Diffusion Transformer

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种融合INT8 GEMM内核，可显著加速消费级安培GPU上的Diffusion Transformer。该新内核允许利用硬件的INT8张量核心，克服了之前使INT8比FP8和NF4替代方案慢的软件限制。优化后的内核实现了2.8-4.2倍更快的GEMM操作，并在更高分辨率下提供了约1.1倍的整体图像生成速度提升，使得在单个消费级GPU上生成1024px图像成为可能。 AI

影响 通过优化模型推理，在消费级硬件上实现更快的图像生成。

排序理由 该集群包含一篇学术论文，详细介绍了AI模型推理的新技术优化。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的INT8内核加速消费级GPU上的Diffusion Transformer

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇学术论文，详细介绍了AI模型推理的新技术优化。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
82 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Ali Asaria, Tony Salomone, Deep Gandhi ·

    在消费级GPU上实现Diffusion Transformer的原生INT8计算：为Ideogram 4.0设计的融合INT8 GEMM内核

    arXiv:2606.14598v1 Announce Type: new Abstract: Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat. We trace this to…

  2. arXiv cs.LG TIER_1 English(EN) · Deep Gandhi ·

    为消费级GPU上的Diffusion Transformer实现原生INT8计算：Ideogram 4.0的融合INT8 GEMM内核

    Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat. We trace this to a software artifact: the production "INT8" forw…

相关实体

相关话题