Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
☆93Dec 2, 2025Updated 2 months ago
Alternatives and similar repositories for SparseSpec
Users that are interested in SparseSpec are comparing it to the libraries listed below
Sorting:
- Python Script to Open SJTU Dormitory Smart Lock☆10Sep 12, 2022Updated 3 years ago
- The official implementation of Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight☆82Jan 16, 2026Updated last month
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆124Feb 22, 2026Updated last week
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆33Nov 29, 2024Updated last year
- Official Implementation of APB (ACL 2025 main Oral) and Spava.☆34Jan 30, 2026Updated last month
- AI model training on heterogeneous, geo-distributed resources☆37Nov 24, 2025Updated 3 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41May 13, 2025Updated 9 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆138Dec 5, 2025Updated 2 months ago
- APEX+ is an LLM Serving Simulator☆42Jun 16, 2025Updated 8 months ago
- Symphony — A decentralized multi-agent framework that enables intelligent agents to collaborate seamlessly across heterogeneous edge devi…☆30Oct 30, 2025Updated 4 months ago
- Prefix-Aware Attention for LLM Decoding☆29Jan 23, 2026Updated last month
- Repo for OSDI 2023 paper: "Ship your Critical Section Not Your Data: Enabling Transparent Delegation with TCLocks"☆21Nov 6, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆358Nov 20, 2025Updated 3 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆210Sep 21, 2024Updated last year
- The official implementation of COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence.☆28Dec 30, 2025Updated 2 months ago
- [ICDCS 2023] Evaluation and Optimization of Gradient Compression for Distributed Deep Learning☆10Apr 28, 2023Updated 2 years ago
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆158Jan 13, 2026Updated last month
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆87Nov 29, 2025Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Aug 6, 2025Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆109Mar 26, 2025Updated 11 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆250Dec 16, 2024Updated last year
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- Compression for Foundation Models☆35Jul 21, 2025Updated 7 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆591Updated this week
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆283Dec 1, 2025Updated 3 months ago
- ☆34Jan 25, 2026Updated last month
- ☆11Aug 13, 2024Updated last year
- [ICLR 2026] BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs☆17May 21, 2025Updated 9 months ago
- Artifact evaluation repo for EuroSys'24.☆29Nov 7, 2023Updated 2 years ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆30Jun 14, 2024Updated last year
- ☆87Jan 22, 2026Updated last month
- LLM Inference with Microscaling Format☆34Nov 12, 2024Updated last year
- ☆35Mar 7, 2025Updated 11 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆193Feb 22, 2026Updated last week
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Jul 10, 2024Updated last year
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Jan 26, 2026Updated last month
- Artifact for "DX100: A Programmable Data Access Accelerator for Indirection (ISCA 2025)" paper☆17Nov 6, 2025Updated 3 months ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆15Jul 10, 2025Updated 7 months ago
- ☆19Jun 1, 2025Updated 8 months ago