---
title: "Discussion on \"My GPU fix was 13% faster on one card and 81% slower on another\" | Hashnode"
description: "Discussion on \"My GPU fix was 13% faster on one card and 81% slower on another\". A vLLM int8 GEMM change, a reviewer with a smaller Ada GPU, and the one idea that explained it: waves"
url: "https://hashnode.com/posts/gpu-fix-faster-on-one-card-slower-on-another-waves/6adf75af7a752cdd73090b42"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [My GPU fix was 13% faster on one card and 81% slower on another](https://amankarki.hashnode.dev/gpu-fix-faster-on-one-card-slower-on-another-waves?utm_source=hashnode&utm_medium=feed)

A vLLM int8 GEMM change, a reviewer with a smaller Ada GPU, and the one idea that explained it: waves

Oct 26 · 7 min read · amankarki.hashnode.dev  
Read the article

-   [#cuda](https://hashnode.com/tag/cuda)
-   [#gpu](https://hashnode.com/tag/gpu)
-   [#vllm](https://hashnode.com/tag/vllm)
-   [#performance](https://hashnode.com/tag/performance)
-   [#opensource](https://hashnode.com/tag/opensource)

## Written by

[Aman Karki](https://hashnode.com/@amankarki)

@amankarki · India

  
[View profile](https://hashnode.com/@amankarki)

C++/CUDA Engineer · LLM Inference & Systems

C++/CUDA engineer building LLM inference and GPU code from scratch: verbum.cpp, Lattice, RAAG. 2 CUDA PRs merged into llama.cpp. I write about inference, GPU performance, and measuring things honestly.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
