[ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning
☆36Sep 12, 2025Updated last year
Alternatives and similar repositories for LessIsMore
Users that are interested in LessIsMore are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated 11 months ago
- ☆17Jun 15, 2026Updated 3 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆120Dec 2, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆88Sep 15, 2025Updated last year
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆68Aug 22, 2026Updated 3 weeks ago
- ASPLOS'24: Optimal Kernel Orchestration for Tensor Programs with Korch☆42Mar 27, 2025Updated last year
- ☆17May 10, 2024Updated 2 years ago
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆29Apr 25, 2023Updated 3 years ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆314May 1, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2026] Draft-based Approximate Inference for LLMs☆21Mar 10, 2026Updated 6 months ago
- ☆30Oct 3, 2022Updated 3 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆407Jul 10, 2025Updated last year
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆221Jul 10, 2026Updated 2 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 9 months ago
- ☆12Apr 29, 2024Updated 2 years ago
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆19Feb 9, 2026Updated 7 months ago
- ☆27May 12, 2026Updated 4 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 10 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆13Jun 2, 2026Updated 3 months ago
- Compact and Agent-Native MoE Training System☆352Updated this week
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆49Nov 5, 2024Updated last year
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"☆48Jul 29, 2025Updated last year
- ☆14Oct 3, 2024Updated last year
- [ICML 2026] Official implementation of "FOCUS: DLLMs Know How to Tame Their Compute Bound".☆19Aug 2, 2026Updated last month
- Code for reproducing experiments performed for Accoridon☆13Jun 11, 2021Updated 5 years ago
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆21Jan 24, 2025Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆140Nov 26, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- letta integration for terminalbench (#1 open source agent, in under 200 lines of code)☆19Oct 22, 2025Updated 10 months ago
- [VLDB 26, NeurIPS 25] Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆152Sep 14, 2026Updated last week
- DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning☆20Nov 11, 2025Updated 10 months ago
- ☆88Jun 16, 2025Updated last year
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆82Dec 25, 2025Updated 8 months ago
- LightRFT (Light Reinforcement Fine-Tuning) is an advanced reinforcement learning fine-tuning framework designed for Large Language Models…☆19Jan 12, 2026Updated 8 months ago
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆16Nov 4, 2025Updated 10 months ago