[ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading
☆27Jan 6, 2026Updated 9 months ago
Alternatives and similar repositories for ISCA-2025-LIA
Users that are interested in ISCA-2025-LIA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading☆12Jun 28, 2025Updated last year
- 面向长对话场景的 AI 对话阅读与跳转增强插件。在页面中提供 Prompt 侧边栏、上下快速导航和当前回复大纲，帮助你更高效地浏览、定位和回看整段对话内容。☆19Mar 11, 2026Updated 7 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆98Jun 16, 2025Updated last year
- Contain some materials about CXL.☆20Feb 29, 2024Updated 2 years ago
- A curated list of open-source projects that help leverage CXL technology.☆30Sep 26, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆12Nov 8, 2024Updated last year
- The simulator for SPADA, an SpGEMM accelerator with adaptive dataflow☆47Jan 26, 2023Updated 3 years ago
- 使用 CLI 进行中科院计算所上网认证登陆☆12Sep 23, 2025Updated last year
- Tiered Memory Management Beyond Hotness (OSDI'25)☆37Jul 31, 2025Updated last year
- ☆19Sep 26, 2026Updated last month
- Codes for our ADMS'24 paper "Bandwidth Expansion via CXL: A Pathway to Accelerating In-Memory Analytical Processing".☆10Nov 8, 2024Updated last year
- Artifact for "DX100: A Programmable Data Access Accelerator for Indirection (ISCA 2025)" paper☆22Nov 6, 2025Updated 11 months ago
- ☆14Oct 22, 2026Updated last week
- A full-system, cycle-level simulator based on gem5 that provides complete support for all three CXL sub-protocols and all three types of …☆173May 11, 2026Updated 5 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.
- ☆25Updated this week
- ☆17Jun 25, 2024Updated 2 years ago
- Distributed AI/HPC Monitoring Framework☆29Apr 11, 2025Updated last year
- ☆27Apr 13, 2025Updated last year
- ☆12Nov 24, 2023Updated 2 years ago
- A Python tool for tracking changes in Compute Express Link (CXL) features within the Linux kernel using GitHub API. It supports various o…☆13Jun 23, 2026Updated 4 months ago
- ☆21May 11, 2026Updated 5 months ago
- ☆16May 9, 2022Updated 4 years ago
- Pin based tool for simulation of rack-scale disaggregated memory systems☆33Mar 8, 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.
- Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching☆43Jul 10, 2024Updated 2 years ago
- Artifact for paper "PIM is All You Need: A CXL-Enabled GPU-Free System for LLM Inference", ASPLOS 2025☆148Aug 22, 2026Updated 2 months ago
- InstAttention: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference☆19Mar 30, 2025Updated last year
- ☆11Apr 21, 2022Updated 4 years ago
- ☆26Dec 4, 2020Updated 5 years ago
- ☆11Apr 16, 2023Updated 3 years ago
- A project for Advanced Operating System(CS604) that implements ARC cache replacement policy.☆20Aug 23, 2020Updated 6 years ago
- General Stride K-Nearest Neighbors☆14Jun 15, 2021Updated 5 years ago
- Note repository for studying Peripheral Component Interconnect Express (PCIe) and Compute Express Link (CXL).☆17Feb 17, 2025Updated last year
- 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.
- Distributed Communication-Optimal LU-factorization Algorithm☆12Aug 1, 2021Updated 5 years ago
- Artifact source and scripts for the paper "Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis"☆10Feb 17, 2021Updated 5 years ago
- A unified simulation platform that combines hardware and software, enabling pre-silicon, full-stack, closed-loop evaluation of your robot…☆48Oct 21, 2026Updated last week
- CAM: Asynchronous GPU-Initiated, CPU-Managed SSD Management for Batching Storage Access [ICDE'25]☆20Mar 3, 2025Updated last year
- ☆17Jun 4, 2026Updated 4 months ago
- 并行与分布式计算导论大作业☆26Dec 26, 2019Updated 6 years ago
- ☆77Aug 4, 2026Updated 2 months ago