Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
☆122Dec 2, 2025Updated 11 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☆69Aug 22, 2026Updated 2 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆110Aug 31, 2026Updated 2 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆255Nov 19, 2025Updated 11 months ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆211Apr 21, 2026Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆55Dec 17, 2024Updated last year
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated last year
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)☆49Feb 10, 2026Updated 9 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆351Jul 2, 2024Updated 2 years ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆26Feb 21, 2025Updated last year
- Prefix-Aware Attention for LLM Decoding☆51May 26, 2026Updated 5 months ago
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆141Jul 25, 2026Updated 3 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆77Oct 2, 2025Updated last year
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆313Dec 1, 2025Updated 11 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆227Mar 18, 2026Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- This is a minimal artifact with state-of-the-art speculative decoding as described in the SwiftSpec paper [ASPLOS' 26].☆14Mar 24, 2026Updated 7 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.
- [NeurIPS 2025] Speculate Deep and Accurate☆25Aug 10, 2026Updated 3 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆869Mar 6, 2025Updated last year
- [ICLR 2026] Draft-based Approximate Inference for LLMs☆24Mar 10, 2026Updated 8 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆315Updated this week
- Preview Code for Continuum Paper☆113Oct 26, 2026Updated 3 weeks ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆77Mar 17, 2026Updated 8 months ago
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆59Jun 17, 2025Updated last year
- 16-fold memory access reduction with nearly no loss☆107Mar 26, 2025Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- 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.
- Accepted to MLSys 2026☆98Apr 19, 2026Updated 6 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆168Feb 20, 2025Updated last year
- UniQL official repository (ICLR 2026)☆19Jan 27, 2026Updated 9 months ago
- ☆83Aug 21, 2024Updated 2 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,579Feb 20, 2026Updated 8 months ago
- A sparse attention kernel supporting mix sparse patterns☆566Jan 18, 2026Updated 10 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆712Jul 4, 2026Updated 4 months ago
Are these results useful?