SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
read the original abstract
We introduce SeerAttention-R, a sparse attention framework specifically tailored for the long decoding of reasoning models. Extended from SeerAttention, SeerAttention-R retains the design of learning attention sparsity through a self-distilled gating mechanism, while removing query pooling to accommodate auto-regressive decoding. With a lightweight plug-in gating, SeerAttention-R is flexible and can be easily integrated into existing pretrained model without modifying the original parameters. We demonstrate that SeerAttention-R, trained on just 0.4B tokens, maintains near-lossless reasoning accuracy with 4K token budget in AIME benchmark under large sparse attention block sizes (64/128). Using TileLang, we develop a highly optimized sparse decoding kernel that achieves near-theoretical speedups of up to 9x over FlashAttention-3 on H100 GPU at 90% sparsity. Code is available at: https://github.com/microsoft/SeerAttention.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
DELTA partitions layers into full, delta, and sparse groups to select salient tokens via aggregated attention scores, matching full-attention accuracy on AIME and GPQA while cutting attended tokens up to 4.25x and ach...
-
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
CLSA shares both KV cache and routing indices across decoder layers to amortize top-k selection, delivering up to 7.6x decoding speedup and 17.1x throughput at 128K context while preserving accuracy.
-
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
DashAttention introduces differentiable adaptive sparse hierarchical attention via α-entmax block selection, achieving full-attention accuracy at 75% sparsity with improved Pareto performance over NSA and InfLLMv2.
-
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
-
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
SPIN co-designs sparse attention with hierarchical memory to achieve 1.66-5.66x higher throughput, 7-9x lower TTFT, and up to 58% lower TPOT than vLLM and original sparse implementations.
-
BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
BLASST dynamically sparsifies attention by thresholding softmax scores to skip blocks, delivering 1.5x speedups at 70%+ sparsity while preserving benchmark accuracy.
-
An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
Fluxion achieves 1.5x-3.7x speedup in long-context LLM inference with CPU KV caches while limiting accuracy degradation to at most 0.26 relative to full attention.
-
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
-
Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
Unifying LLM memory optimizations into a Prepare-Compute-Retrieve-Apply pipeline and accelerating it on GPU-FPGA hardware yields up to 2.2x faster inference and 4.7x less energy than GPU-only baselines.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.