SSV presents a sparse speculative-verification framework that resolves mismatches between speculative decoding and dynamic sparse attention to deliver up to 3.49x end-to-end throughput and 6.86x kernel speedups on NVIDIA H100 GPUs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.OS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SSV: Sparse Speculative Verification for Efficient LLM Inference
SSV presents a sparse speculative-verification framework that resolves mismatches between speculative decoding and dynamic sparse attention to deliver up to 3.49x end-to-end throughput and 6.86x kernel speedups on NVIDIA H100 GPUs.