Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
☆133Dec 3, 2024Updated last year
Alternatives and similar repositories for tree_attention
Users that are interested in tree_attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 3 months ago
- Linear Attention Sequence Parallelism (LASP)☆87Jun 4, 2024Updated 2 years ago
- Ring attention implementation with flash attention☆1,025Sep 10, 2025Updated 9 months ago
- [COLM'25] A Controlled Study on Long Context Extension and Generalization in LLMs☆65Mar 9, 2026Updated 3 months ago
- ☆321Jul 10, 2025Updated 11 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Large Context Attention☆773Oct 13, 2025Updated 8 months ago
- LLM KV cache compression made easy☆1,123Updated this week
- Latent Large Language Models☆19Aug 24, 2024Updated last year
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆31Aug 19, 2025Updated 10 months ago
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Feb 2, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,221Apr 8, 2026Updated 2 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆156Apr 7, 2025Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆538Feb 10, 2025Updated last year
- 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.
- ring-attention experiments☆169Oct 17, 2024Updated last year
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆26Oct 10, 2025Updated 8 months ago
- Efficient LLM Inference over Long Sequences☆393Jun 25, 2025Updated last year
- JAX bindings for Flash Attention v2☆108Feb 28, 2026Updated 4 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,008Feb 5, 2026Updated 5 months ago
- A repository for research on medium sized language models.☆78May 23, 2024Updated 2 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated 2 years ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆345Feb 23, 2025Updated last year
- ☆56Nov 6, 2024Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ACL 24 Findings] Implementation of Resonance RoPE and the PosGen synthetic dataset.☆24Mar 5, 2024Updated 2 years ago
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- ☆34May 14, 2025Updated last year
- A toolkit for scaling law research ⚖☆68Jan 27, 2025Updated last year
- ☆29Aug 30, 2024Updated last year
- Helpful tools and examples for working with flex-attention☆1,205Jun 27, 2026Updated last week
- ACL 2023☆39Jun 6, 2023Updated 3 years ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆675May 21, 2026Updated last month
- 🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.☆312Jun 29, 2026Updated last week
- 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.
- OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training☆579Jun 10, 2026Updated 3 weeks ago
- Sparse Backpropagation for Mixture-of-Expert Training☆30Jul 2, 2024Updated 2 years ago
- ☆54May 20, 2024Updated 2 years ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆360Updated this week
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆53Oct 18, 2024Updated last year
- An implementation of the Llama architecture, to instruct and delight☆21May 31, 2025Updated last year
- [TMLR 2025] When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models☆126Mar 6, 2026Updated 3 months ago