[ICML 2026] Sparser Block-Sparse Attention via Token Permutation
☆33May 22, 2026Updated 5 months ago
Alternatives and similar repositories for pbs-attn
Users that are interested in pbs-attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2026] Prism: Spectral-Aware Block-Sparse Attention☆27May 22, 2026Updated 5 months ago
- Official repository for the EMNLP 2025 paper “UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets”.☆16Sep 19, 2025Updated last year
- [EMNLP Findings'25] Official PyTorch Implementation of Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Align…☆16Sep 19, 2025Updated last year
- [AAAI 2024] DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning☆15Apr 29, 2024Updated 2 years ago
- The official implementation of "Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation"☆25Feb 8, 2026Updated 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.
- ☆19Nov 6, 2023Updated 3 years ago
- Official PyTorch implementation of [PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation](https://arxiv.org/abs…☆25Jan 25, 2026Updated 9 months ago
- A training-free method for extending the maximum context length of language models☆14Oct 6, 2025Updated last year
- An imaginary extension of rotary position embeddings for long-context language models☆35Dec 9, 2025Updated 11 months ago
- [ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments☆40Feb 17, 2025Updated last year
- Inference-time alignment for harmlessness through cross-model guidance (ACL 2024). Code + MM-Harmful Bench.☆38Oct 2, 2024Updated 2 years ago
- ☆27Jan 29, 2026Updated 9 months ago
- Code for M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models☆23Jul 27, 2024Updated 2 years ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated last year
- 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.
- ☆12Jun 6, 2026Updated 5 months ago
- An 11B model for real-time video understanding with gated cross-attention and streaming inference☆175Jul 16, 2026Updated 4 months ago
- A multi-user OpenClaw deployment with isolated workspaces and configurable model backends☆25Mar 30, 2026Updated 7 months ago
- Official implementation of X-Slim(xslim): Accelerating diffusion model via Extreme-slimming Caching☆12Feb 25, 2026Updated 8 months ago
- OpenMOSS presents a collection of our research on LLMs, supported by SII, Fudan and Mosi.☆33Updated this week
- Create SSH and TCP Proxy to your company container.☆35Nov 5, 2026Updated last week
- ☆18Oct 31, 2026Updated 2 weeks ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆224Jul 10, 2026Updated 4 months ago
- Methods and code for extending the context length of diffusion language models☆56Dec 7, 2025Updated 11 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆36Dec 10, 2025Updated 11 months ago
- An open-source personal academic homepage template characterized by its user-friendly design and extensive scalability.☆36Updated this week
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆65Jul 1, 2025Updated last year
- [ICML 2025🔥] ParallelComp: Parallel Long-Context Compressor for Length Extrapolation☆30Jun 16, 2025Updated last year
- A tool for better use of Inspire platform (Beta: Codeberg version is more up-to-date)☆31Apr 2, 2026Updated 7 months ago
- Nex-N2.6: Multimodal Agentic Model for Computer Use and Long-Horizon Workflows☆25Nov 11, 2026Updated last week
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated 2 years ago
- A survey of long-context language models covering architecture, infrastructure, training, and evaluation☆65Mar 31, 2025Updated last year
- A proactive robot manipulation model for multimodal physical environments☆125Mar 28, 2026Updated 7 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.
- The evaluation framework for training-free sparse attention in LLMs☆134Jan 27, 2026Updated 9 months ago
- Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers☆24May 26, 2026Updated 5 months ago
- Official code for our paper "Sink-Aware Pruning for Diffusion Language Models"☆13Feb 26, 2026Updated 8 months ago
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- [AAAI 2026] Minute-Long Videos with Dual Parallelisms☆50Mar 25, 2026Updated 7 months ago
- [ICLR 2026] This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Gen…☆54Oct 26, 2026Updated 3 weeks ago
- ☆50May 14, 2026Updated 6 months ago
Are these results useful?