Official codebase for the MLSys 2026 paper "IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference". It enables high-fidelity and high-speed LLM/ViT deployment on ARM CPUs.
☆19May 29, 2026Updated last month
Alternatives and similar repositories for IntAttention
Users that are interested in IntAttention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆19Mar 29, 2026Updated 3 months ago
- ☆17Apr 26, 2026Updated 2 months ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆35May 22, 2026Updated last month
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆17May 20, 2026Updated 2 months ago
- ☆63Jul 21, 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.
- ☆13Aug 23, 2025Updated 10 months ago
- ☆15Jul 25, 2025Updated 11 months ago
- Gate-Level Simulation on a GPU☆10Nov 22, 2016Updated 9 years ago
- Analyze LLM inference: FLOPs, memory, Roofline model. Supports GQA, MoE, MLA, RoPE, SwiGLU. 19 models × 20+ hardware platforms.☆21Apr 16, 2026Updated 3 months ago
- writing really fast kernels☆19Updated this week
- DeDe (OSDI '25): an optimization framework for large-scale resource allocation☆15May 18, 2026Updated 2 months ago
- ☆11Aug 8, 2018Updated 7 years ago
- a minimal paged attention implementation☆20Jan 30, 2026Updated 5 months ago
- Tempo is a system for declarative, efficient, end-to-end compiled dynamic deep learning☆30Oct 21, 2025Updated 8 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.
- ✍️ Parser for the conventional commits specification☆10Nov 5, 2025Updated 8 months ago
- 🦖 Designed for collecting and sharing Deno news, articles, etc. (Biweekly).☆10Jul 22, 2021Updated 4 years ago
- A lightning-fast Sixel serializer/deserializer☆42Mar 16, 2026Updated 4 months ago
- ☆50Dec 19, 2025Updated 7 months ago
- Batched square compact-Householder QR factorization.☆14Jul 2, 2026Updated 2 weeks ago
- 🔥 [ICML'26] ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs☆30Jun 29, 2026Updated 3 weeks ago
- IntelliJ platform plugin for Wavefront OBJ format☆15Jul 4, 2026Updated 2 weeks ago
- Debug adapter for Minecraft datapacks, enabling breakpoints, step execution, and game-state inspection directly in VSCode.☆16Apr 12, 2026Updated 3 months ago
- A mod for Raft to name the shark randomly after, for example, twitch subscribers☆10Jun 30, 2022Updated 4 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Portal Compose Navigation☆13Apr 24, 2026Updated 2 months ago
- LLM-DSE: Searching Accelerator Parameters with LLM Agents☆16May 22, 2025Updated last year
- Type-safe NBT parser with kotlinx.serialization, SNBT and JSON support.☆13Mar 4, 2023Updated 3 years ago
- ☆19Dec 21, 2020Updated 5 years ago
- Generate release notes based on GitHub Commits☆13Jun 25, 2022Updated 4 years ago
- ☆21Mar 3, 2025Updated last year
- Kotlin/JS bindings for PIXI.js library.☆15Oct 30, 2022Updated 3 years ago
- A typescript Discord Bot.☆11May 21, 2017Updated 9 years ago
- SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs (ICML 2025)☆36Nov 28, 2025Updated 7 months ago
- 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.
- ☆18Jul 31, 2023Updated 2 years ago
- ☆71Mar 24, 2026Updated 3 months ago
- A kotlin multiplatform experiment for representing app navigation with tree like data structures☆22May 14, 2026Updated 2 months ago
- This project is a "source code cover" of the song "HelloWorld.java" by Nanowar of Steel... except it's now "HelloWorld.kt" and it's deliv…☆13Dec 3, 2024Updated last year
- Pytorch implements the VGG19 model to classify cifar100☆12Feb 16, 2019Updated 7 years ago
- Providing wrapper types for safely performing panic-free checked arithmetic on instants and durations.☆17Jul 11, 2026Updated last week
- AI model training on heterogeneous, geo-distributed resources☆46Nov 24, 2025Updated 7 months ago