Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
☆138Dec 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 7 months ago
- Training hybrid models for dummies.☆30Nov 1, 2025Updated last year
- Linear Attention Sequence Parallelism (LASP)☆87Jun 4, 2024Updated 2 years ago
- Ring attention implementation with flash attention☆1,067Sep 10, 2025Updated last year
- Large Context Attention☆775Oct 13, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆345Feb 23, 2025Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- [COLM'25] A Controlled Study on Long Context Extension and Generalization in LLMs☆65Mar 9, 2026Updated 7 months ago
- ☆57Nov 6, 2024Updated 2 years ago
- A repository for research on medium sized language models.☆78May 23, 2024Updated 2 years ago
- [TMLR 2025] When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models☆126Mar 6, 2026Updated 8 months ago
- Overflow Prevention Enhances Long-Context Recurrent LLMs (COLM 2025)☆19Jul 8, 2025Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆438Nov 20, 2025Updated 11 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆19Mar 15, 2024Updated 2 years 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.
- Efficient LLM Inference over Long Sequences☆392Jun 25, 2025Updated last year
- ☆336Jul 10, 2025Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆11Dec 13, 2023Updated 2 years ago
- LLM KV cache compression made easy☆1,245Updated this week
- Code and dataset for the paper "IsarStep: a Benchmark for High-level Mathematical Reasoning"☆12Mar 15, 2021Updated 5 years ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Apr 17, 2024Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆23Mar 15, 2024Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆548May 16, 2025Updated last year
- ☆18Sep 22, 2024Updated 2 years ago
- 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.
- ☆312Apr 23, 2025Updated last year
- 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
- Code and data to explore neural scaling laws of xLSTM and Transformer models.☆24Updated this week
- ☆14Oct 3, 2024Updated 2 years ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,232Oct 10, 2026Updated 3 weeks ago
- Helpful tools and examples for working with flex-attention☆1,263Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆696Sep 16, 2026Updated last month
- Latent Large Language Models☆19Aug 24, 2024Updated 2 years ago
- Kernel Library for Large Headdim Attention (64~1024, BF16/FP8/FP4), 1.5x~15x↑ vs PyTorch SDPA.☆346Updated this week
- 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.
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆75May 26, 2024Updated 2 years ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,025Feb 5, 2026Updated 9 months ago
- ☆54May 20, 2024Updated 2 years ago
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆83Jan 18, 2024Updated 2 years ago
- Multipack distributed sampler for fast padding-free training of LLMs☆207Aug 10, 2024Updated 2 years ago
- Sparse Backpropagation for Mixture-of-Expert Training☆30Jul 2, 2024Updated 2 years ago
- ACL 2023☆38Jun 6, 2023Updated 3 years ago