[NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning
☆26Dec 5, 2025Updated 9 months ago
Alternatives and similar repositories for MultipoleAttention
Users that are interested in MultipoleAttention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆58Nov 20, 2024Updated last year
- The official implementation of NOSA☆19Jun 11, 2026Updated 3 months ago
- ☆22Feb 5, 2024Updated 2 years ago
- [ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression☆53Aug 7, 2025Updated last year
- ☆14Oct 3, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ICLR 2026] ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs☆47Mar 27, 2026Updated 5 months ago
- Efficient and Scalable Estimation of Tool Representations in Vector Space☆32Sep 5, 2024Updated 2 years ago
- Official implementation of LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents☆32Updated this week
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆33Apr 14, 2026Updated 5 months ago
- ☆11May 24, 2024Updated 2 years ago
- [ICLR 2026] Draft-based Approximate Inference for LLMs☆21Mar 10, 2026Updated 6 months ago
- ☆34Oct 13, 2025Updated 11 months ago
- ☆13Jul 15, 2024Updated 2 years ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- 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.
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆225Feb 11, 2026Updated 7 months ago
- The code used to train and run inference with the ColQwen3 model. Welcome to follow and star! ⭐️⭐️⭐️ https://huggingface.co/goodman2001/…☆16Aug 16, 2026Updated last month
- ☆18Sep 23, 2025Updated last year
- Open Source Projects from Pallas Lab☆21Oct 10, 2021Updated 4 years ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Sep 10, 2024Updated 2 years ago
- [ICML 2026] Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆61Jun 28, 2026Updated 2 months ago
- ☆20Mar 19, 2025Updated last year
- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts☆16Jul 27, 2026Updated last month
- Reimplementation of VFDT and EFDT. Our codebase is simple, concise, easy to reproduce with strong performances.☆10Feb 1, 2021Updated 5 years ago
- 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.
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆69Oct 31, 2025Updated 10 months ago
- Source codes of "Fast Continuous Subgraph Matching over Streaming Graphs via Backtracking Reduction", SIGMOD 2023☆14Sep 7, 2023Updated 3 years ago
- Advancing the frontier of efficient AI☆69Updated this week
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15May 19, 2026Updated 4 months ago
- ☆16Oct 23, 2023Updated 2 years ago
- TurboQuant reference implementation — KV cache compression with engineering insights (ICLR 2026 paper reproduction)☆17Mar 28, 2026Updated 5 months ago
- ☆16Jul 30, 2025Updated last year
- ☆65Jun 12, 2025Updated last year
- [ACL 2025 Main] Official Pytorch Implementation for "State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Mod…☆15Jun 9, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- GPU accelerated Perlin Noise in python☆11Oct 23, 2020Updated 5 years ago
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆17Jan 4, 2026Updated 8 months ago
- Mutual Information Gradient Estimation☆12Sep 8, 2021Updated 5 years ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated 11 months ago
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆16May 25, 2026Updated 4 months ago
- VideoNSA: Native Sparse Attention Scales Video Understanding☆90Nov 16, 2025Updated 10 months ago
- [TrimKV] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs - [DBTrimKV] Make Each Token Count: Towards Improving Lo…☆21Jul 26, 2026Updated last month