SparseEngine: Sparse-First Inference Engine
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/CURRENTF/SparseEngine
Sources
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Palu: Compressing KV-Cache with Low-Rank Projection
- The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
- Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- The Llama 3 Herd of Models
- vToken: Token-Level Virtualization for Reclaimable KV Caches
- ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
- Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving
- MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
- Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
- Gemma 4 Technical Report
- HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management
- Qwen3 Technical Report
- Qwen2.5 Technical Report
- ReAct: Synergizing Reasoning and Acting in Language Models
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks