SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2505.11594 · 2025

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
copy not recorded — 0 of 3
FunctionStatusWhere it lives
sageattn Not yet run this paper's copy was not recorded; identical code first harvested from thu-ml/sageattention
pointer only · get_code("0d53f0eb082706d1")
sageattn_qk_int8_pv_fp16_triton Not yet run this paper's copy was not recorded; identical code first harvested from thu-ml/sageattention
pointer only · get_code("b342df7dc419a801")
sageattn_varlen Not yet run this paper's copy was not recorded; identical code first harvested from thu-ml/sageattention
pointer only · get_code("c9ff307a043756a1")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention computation. Our implementation achieves 1038 TOPS on RTX5090, which is a 5x speedup over the fastest FlashAttention on RTX5090. Experiments show that our FP4 attention can accelerate inference of various models in a plug-and-play way. Second, we pioneer low-bit attention to training tasks. Existing low-bit attention works like FlashAttention3 and SageAttention focus only on inference. However, the efficiency of training large models is also important. To explore whether low-bit attention can be effectively applied to training tasks, we design an accurate and efficient 8-bit attention for both forward and backward propagation. Experiments indicate that 8-bit attention achieves lossless performance in fine-tuning tasks but exhibits slower convergence in pretraining tasks. The code is available at https://github.com/thu-ml/SageAttention.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2505.11594")
get_code_for_paper("2505.11594")
have("2505.11594")

Connect an agent — have() is free.