SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling
☆16Aug 14, 2025Updated last year
Alternatives and similar repositories for UltraAttn
Users that are interested in UltraAttn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- ☆46Oct 15, 2025Updated last year
- ☆37Aug 7, 2025Updated last year
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- ☆10Oct 22, 2026Updated last 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.
- ☆12Oct 23, 2025Updated last year
- ☆16Jul 19, 2026Updated 3 months ago
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆33Aug 6, 2026Updated 2 months ago
- Resource Multiplexing in Tuning and Serving Large Language Models (USENIX ATC 2025)☆10Apr 21, 2026Updated 6 months ago
- ☆137Nov 11, 2024Updated last year
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆18Aug 6, 2026Updated 2 months ago
- Minimal PyTorch implementation of TP, SP, FSDP and sharded-EMA☆32Nov 27, 2025Updated 11 months ago
- ☆17Jun 4, 2026Updated 4 months 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.
- Megakernel for Gated DeltaNet, optimized by PTO-ISA☆23Oct 19, 2026Updated last week
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆56Sep 23, 2026Updated last month
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 6 months ago
- ☆12Nov 21, 2025Updated 11 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆79Aug 8, 2026Updated 2 months ago
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆26Aug 5, 2026Updated 2 months ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 months ago
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- ☆19Jun 3, 2023Updated 3 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.
- An open, visual atlas of looped transformers, recurrent computation, adaptive depth, and latent reasoning.☆33Sep 26, 2026Updated last month
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated 4 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- a size profiler for cuda binary☆74Oct 3, 2026Updated 3 weeks ago
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 6 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆300Sep 25, 2026Updated last month
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 8 months ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆224Mar 18, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- High-Throughput Batch Inference☆18Oct 21, 2026Updated last week
- CUDA Graph runtime tensor debugging utilities for PyTorch☆18Jul 12, 2026Updated 3 months ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆33May 12, 2026Updated 5 months ago
- Reverse-engineered instruction set architecture database for NVIDIA SM120 (Blackwell) GPUs.☆25Updated this week
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆122Dec 2, 2025Updated 10 months ago
- [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization☆24Apr 13, 2026Updated 6 months ago
- How to plot for papers, slides, demos, etc.☆10Apr 7, 2022Updated 4 years ago