Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
☆115Dec 2, 2025Updated 7 months ago
Alternatives and similar repositories for SparseSpec
Users that are interested in SparseSpec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆67Jun 24, 2026Updated 3 weeks ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆105Jul 8, 2026Updated last week
- ☆250Nov 19, 2025Updated 8 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆174Feb 27, 2026Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆154Dec 4, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆56Aug 6, 2025Updated 11 months ago
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)☆49Feb 10, 2026Updated 5 months ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆198Apr 21, 2026Updated 2 months ago
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆34Sep 12, 2025Updated 10 months ago
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆26Feb 21, 2025Updated last year
- [NeurIPS 2025] Speculate Deep and Accurate☆21Jan 16, 2026Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆54Dec 17, 2024Updated last year
- Prefix-Aware Attention for LLM Decoding☆41May 26, 2026Updated last month
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆120Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆281Aug 31, 2024Updated last year
- [ICLR 2026] Draft-based Approximate Inference for LLMs☆21Mar 10, 2026Updated 4 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆731Jul 4, 2026Updated 2 weeks ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆418Nov 20, 2025Updated 8 months ago
- UniQL official repository (ICLR 2026)☆16Jan 27, 2026Updated 5 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆343Jul 2, 2024Updated 2 years ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆304Dec 1, 2025Updated 7 months ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆71Mar 17, 2026Updated 4 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆210Mar 18, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆754Jun 2, 2026Updated last month
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated 11 months ago
- ☆82Aug 21, 2024Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆400Jul 10, 2025Updated last year
- mKernel: fast multi-node, multi-GPU fused kernels☆251Jun 21, 2026Updated 3 weeks ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆54Jun 17, 2025Updated last year
- Preview Code for Continuum Paper☆89Jul 13, 2026Updated last week
- Accepted to MLSys 2026☆91Apr 19, 2026Updated 3 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Building the Virtuous Cycle for AI-driven LLM Systems☆259May 1, 2026Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆850Mar 6, 2025Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆692Jul 4, 2026Updated 2 weeks ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆321Feb 24, 2026Updated 4 months ago
- Artifact Evaluation for SOSP 2025☆21Aug 16, 2025Updated 11 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆63Mar 5, 2025Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆192Jul 10, 2024Updated 2 years ago