Papers › Optimization of Armv9 architecture general large language model inference performance...

Optimization of Armv9 architecture general large language model inference performance based on Llama.cpp

16 Jun 2024arXiv:2406.10816archive 2025-07-28

Longhao Chen, Yina Zhao, Qiangjun Xie, Qinghua Sheng

This article optimizes the inference performance of the Qwen-1.8B model by performing Int8 quantization, vectorizing some operators in llama.cpp, and modifying the compilation script to improve the compiler optimization level. On the Yitian 710 experimental platform, the prefill performance is increased by 1.6 times, the decoding performance is increased by 24 times, the memory usage is reduced to 1/5 of the original, and the accuracy loss is almost negligible.

PaperPDFCode

Code

longhao-chen/aicas2024 officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Compiler OptimizationLanguage ModelingLanguage ModellingLarge Language ModelQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections