UnionSparse combines a shared-bitmap sparse format with a Tensor Core SpMM kernel to speed up low-bit sparse LLM decoding on edge GPUs by cutting index traffic.
Hqp: Sensitivity-aware hybrid quantization and pruning for ultra-low-latency edge ai inference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge
UnionSparse combines a shared-bitmap sparse format with a Tensor Core SpMM kernel to speed up low-bit sparse LLM decoding on edge GPUs by cutting index traffic.