Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Quick Take
RTPurbo transforms full attention models into sparse ones with minimal adaptation, achieving efficiency gains.
Key Points
- Full attention models are intrinsically sparse.
- RTPurbo uses a lightweight token indexer for efficiency.
- Achieves up to 9.36× speedup with near-lossless accuracy.
📖 Reader Mode
~2 min readAbstract:Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable trade-off among efficiency, training cost, and accuracy. In this work, we show that full-attention LLMs are already intrinsically sparse and can be transformed into highly sparse models with only minimal adaptation. Our approach is built on three observations: (1) only a small subset of attention heads truly requires full long-context processing; (2) long-range retrieval is governed primarily by a low-dimensional subspace, allowing relevant tokens to be retrieved efficiently with a 16-dimensional indexer; and (3) the useful token budget is strongly query-dependent, making dynamic top-$p$ selection more suitable than fixed top-$k$ sparsification. Based on these insights, we propose RTPurbo, which retains the full KV cache only for retrieval heads and introduces a lightweight token indexer for sparse attention. By exploiting the model's intrinsic sparsity, RTPurbo achieves sparsification with only a few hundred training steps. Experiments on long-context benchmarks and reasoning tasks show that RTPurbo preserves near-lossless accuracy while delivering substantial efficiency gains, including up to a 9.36$\times$ prefill speedup at 1M context and about a 2.01$\times$ decode speedup. These results suggest that strong sparse inference can be obtained from standard full-attention training without expensive native sparse pretraining.
| Comments: | 20 pages, 9 figures |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.16928 [cs.CL] |
| (or arXiv:2605.16928v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16928 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanke Zhou [view email]
[v1]
Sat, 16 May 2026 10:51:58 UTC (2,772 KB)
— Originally published at arxiv.org
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The reliability of LLM judges for evaluating deep research agents is critically assessed using the REFLECT benchmark.