# Celty: SpMSpV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference

arXiv: https://arxiv.org/abs/2608.01536 · HTML: https://mlsanity.com/paper/2608.01536/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Sparse GPU Kernels for Deep Learning](https://mlsanity.com/paper/2006.10901/) (2020)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference](https://mlsanity.com/paper/2504.19449/) (2025)
- [2SSP: A Two-Stage Framework for Structured Pruning of LLMs](https://mlsanity.com/paper/2501.17771/) (2025)
- [DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs](https://mlsanity.com/paper/2506.20194/) (2025)
- [MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity](https://mlsanity.com/paper/2511.13061/) (2025)
- [Accelerating a Triton Fused Kernel for W4A16 Quantized Inference with SplitK work decomposition](https://mlsanity.com/paper/2402.00025/) (2024)
- [Adaptive SpMV/SpMSpV on GPUs for Input Vectors of Varied Sparsity](https://mlsanity.com/paper/2006.16767/) (2020)

## Abstract (arXiv)

Large Language Models (LLMs) increasingly rely on sparsity to cut inference cost, but most prior work exploits a single sparsity source and targets batched multi-user inference. Dual-sparsity, which pairs unstructured weight pruning with runtime activation sparsity, offers a compelling size-accuracy-latency tradeoff for single-user decoding, but forms a Sparse Matrix-Sparse Vector (SpMSpV) workload that existing GPU kernels handle poorly. We propose Celty, a co-designed sparse format, GPU kernel, and SIMT microarchitecture for SpMSpV in LLM inference. Celty's Run-Length Compressed CSC (RLC-CSC) format enables vectorized loading of compressed weight columns and exploits both sparsity sources to skip memory accesses, accumulating partial products in shared memory. The Celty Sparse SIMT Core then adds a pipelined RLC decoder that removes software index reconstruction and repurposes local register files for conflict-free accumulation, operating on the same compressed representation. The kernel alone achieves up to 2.8x over cuBLAS; with the Sparse SIMT Core, speedup reaches 5.3x over cuBLAS at 70% dual-sparsity.