paper-with-me

홈 › Papers

Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0

2026-06-12 · Ali Asaria, Tony Salomone, Deep Gandhi arxiv

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" forward quantizes weights and activations only to immediately dequantize them back to bf16 and run a bf16 matrix multiply, never engaging the GPU's INT8 tensor cores, so the hardware's compute advantage is left entirely unrealized. We close this gap with a single fused Triton INT8 GEMM (int8xint8->int32 on Ampere tensor cores, with per-token x per-channel dequantization and bias folded into the epilogue, autotuned per GEMM shape) dropped into the Ideogram 4.0 diffusion transformer's linear layers in place of the dequantize-to-bf16 path. In the kernel, the int8xint8->int32 accumulation is bit-exact against torch._int_mm and the dequantized output matches the reference at cosine similarity 1.0 with no NaNs, running 2.8-4.2x faster than bf16 per GEMM. End to end it delivers a ~1.1x (~9-10%) speedup at 768px, and at 1024px it generates an image in 156.5 s on a single RTX 3090, faster than the single-card NF4 (164.5 s) and FP8 (172.9 s) baselines, at no measurable quality cost on these point estimates (PickScore/CLIPScore). INT8 thus goes from the slowest variant to the fastest, and 1024px becomes single-GPU feasible. The primary speed criterion (beat FP8, by ~9.5%) is comfortably met; the NF4 margin (~4.9%, single-run n=4) is within run-to-run variance we did not quantify and is best read as consistent with meeting the stretch target. We close with an honest deployment map: the win is specific to consumer Ampere, and on A100 and B200 the same kernel loses to those cards' fast native bf16/FP8 paths.

📄 PDF Abstract BibTeX arXiv:2606.14598

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

2026-03-14 · Eshed Gal, Moshe Eliasof, Siddharth Rout, Eldad Haber arxiv

The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spatial state-space block that replaces atte…

Scalable, Tokenization-Free Diffusion Model Architectures with Efficient Initial Convolution and Fixed-Size Reusable Structures for On-Device Image Generation

2024-11-09 · Sanchar Palit, Sathya Veera Reddy Dendi, Mallikarjuna Talluri, Raj Narayana Gadde

Vision Transformers and U-Net architectures have been widely adopted in the implementation of Diffusion Models. However, each architecture presents specific challenges while realizing them on-device. Vision Transformers …

Conditional Image GenerationImage GenerationNoise EstimationUnconditional Image Generation

Co-Scale Conv-Attentional Image Transformers

2021-04-13 · ICCV 2021 10 · Weijian Xu, Yifan Xu, Tyler Chang, Zhuowen Tu

In this paper, we present Co-scale conv-attentional image Transformers (CoaT), a Transformer-based image classifier equipped with co-scale and conv-attentional mechanisms. First, the co-scale mechanism maintains the inte…

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation

The Entropic Bound for Transformers: Why Static Rank Fails and Attention-Native Rank Recovers

2026-07-25 · Byeong Hoon Yoon arxiv

Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is the minimum model capacity required to solve it? We study this through…

Diffusion Bridge Mixture Transports, Schrödinger Bridge Problems and Generative Modeling

2023-04-03 · Stefano Peluchetti

The dynamic Schr\"odinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being closest, in terms of Kullback-Leibler…

valid