TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
☆866Aug 4, 2026Updated 2 months ago
Alternatives and similar repositories for triattention
Users that are interested in triattention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [CVPRW 2026 Oral] Less Detail, Better Answers: Degradation-Driven Prompting for VQA☆20Apr 25, 2026Updated 6 months ago
- [CVPR2026] Exploring Spatial Intelligence from a Generative Perspective☆32Jun 3, 2026Updated 4 months ago
- ☆35Oct 17, 2026Updated last week
- WorldOlympiad: Can Your World Model Survive a Triathlon?☆57Oct 22, 2026Updated last week
- ☆397Apr 16, 2026Updated 6 months ago
- 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.
- Frequency-based KV cache pruning for llama.cpp — 25% cache reduction, improved PPL at long context. GPU compaction kernel for HIP/ROCm.☆16Apr 18, 2026Updated 6 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆345Aug 19, 2026Updated 2 months 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
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,208Aug 18, 2026Updated 2 months ago
- [CVPR2026] Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching☆19Jun 4, 2026Updated 4 months ago
- ☆21Jun 13, 2026Updated 4 months ago
- [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation☆427Jun 3, 2026Updated 4 months ago
- Unsupervised Learning of Generalizable Robot Motion from Compact State Representation☆46Oct 7, 2026Updated 3 weeks ago
- Latent Spatial Memory for Video World Models☆334Aug 27, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The official code of StreamingSwap, a real-time video face swapping method.☆25Oct 20, 2026Updated last week
- Dynamic per-token early exit for LLM inference. Skip layers tokens don't need☆34Sep 18, 2026Updated last month
- high-performance linear attention kernel library built on TileLang☆744Updated this week
- LLM KV cache compression made easy☆1,240Updated this week
- Long Video Gen / World Model / World Action Model (Embodied) Infrastructure☆2,849Updated this week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,265Feb 25, 2026Updated 8 months ago
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,057Apr 23, 2026Updated 6 months ago
- [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.☆526Mar 30, 2026Updated 7 months ago
- Train model and train body.☆48Updated this week
- 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.
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆1,108May 30, 2026Updated 5 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,983Jan 17, 2026Updated 9 months ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,964Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,293Updated this week
- [ACL'26] EvoToken-DLM (Beyond Hard Masks: Progressive Token Evolution for Diffusion Language)☆50Apr 7, 2026Updated 6 months ago
- Algorithms for latent compaction☆277Apr 22, 2026Updated 6 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆785Aug 29, 2026Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆287Jul 6, 2025Updated last year
- A lightweight inference engine supporting speculative speculative decoding (SSD).☆1,019May 10, 2026Updated 5 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.
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆52Mar 25, 2025Updated last year
- Official code for HiLS-Attention☆152Aug 13, 2026Updated 2 months ago
- Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"☆224Dec 29, 2025Updated 10 months ago
- [NeurIPS 2026] DMax: Aggressive Parallel Decoding for dLLMs☆132Sep 28, 2026Updated last month
- Quartet II Official Code☆85May 1, 2026Updated 5 months ago
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,614Oct 23, 2026Updated last week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆204Sep 2, 2026Updated last month