ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviates this by drafting tokens with sparse attention and verifying them with full attention, but existing batched methods remain synchronized: all requests in a batch share a single draft-verify schedule, even though the optimal draft length varies widely across requests and changes dynamically within each request. We propose ASPIRE, a non-synchronized batched self-speculative decoding framework built on three components. First, a unified mixed forward allows drafting and verifying requests to coexist in the same batched forward pass, removing th...
| Authors | Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao et al. |
|---|---|
| Primary category | cs.LG |
| Published | 16 September 2026 |
| Last updated at source | 16 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.