high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia A800

Efficiently Training 7B LLM with 1 Million Sequence Length on 8 GPUs

Pinxue Zhao, Hailin Zhang, Fangcheng Fu, Xiaonan Nie, Qibin Liu, Fang Yang, Yuanbo Peng, Dian Jiao, Shuaipeng Li, Jinbao Xue, Yangyu Tao, Bin Cui

View

Tags: AI, Computer science, CUDA, LLM, Machine learning, NLP, nVidia, nVidia A800

July 28, 2024 by hgpu

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

Zhao Xu, Fan Liu, Hao Liu

View

Tags: AI, Benchmarking, Computer science, nVidia, nVidia A800, Package, Security

June 16, 2024 by hgpu

UVaFTLE: Lagrangian finite time Lyapunov exponent extraction for fluid dynamic applications

Challenging Portability Paradigms: FPGA Acceleration Using SYCL and OpenCL

HPCToolkit

Refining HPCToolkit for application performance analysis at exascale

Open Catalog of Best Practices for Modernization and Optimization

Optimizing the Weather Research and Forecasting Model with OpenMP Offload and Codee

Owl: Differential-based Side-Channel Leakage Detection for CUDA Applications

Owl: Differential-based Side-Channel Leakage Detection for CUDA Applications

pSTL-Bench: Micro-benchmark suite designed to evaluate the scalability and efficiency of parallel C++ STL implementations

Exploring Scalability in C++ Parallel STL Implementations

GPU-Smash: Compression abstraction library

A Parallel Compression Pipeline for Improving GPU Virtualization Data Transfers

Noarr Structures

Abstractions for C++ code optimizations in parallel high-performance applications

SyncPerformance

Characterizing CUDA and OpenMP Synchronization Primitives

$3D-fractal-generators$

3D-fractal-generators

Double-Precision Floating-Point Data Visualizations Using Vulkan API

VerCors: a verification toolset for verifying parallel and concurrent software

The VerCors Verifier: A Progress Report

See all packages

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Login | Sitemap | Feedback | Policy

Contact us: