# Ggml : x2 speed for WASM by optimizing SIMD

**URL:** <https://forum.devtalk.com/t/ggml-x2-speed-for-wasm-by-optimizing-simd/185618>\
**Category:** In The News\
**Tags:** via-news-bot, wasm, in-the-news\
**Created:** [28 January 2025 18:54 UTC](https://forum.devtalk.com/t/ggml-x2-speed-for-wasm-by-optimizing-simd/185618 "2025-01-28T18:54:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [28 January 2025 18:54 UTC](https://forum.devtalk.com/t/ggml-x2-speed-for-wasm-by-optimizing-simd/185618/1 "2025-01-28T18:54:51Z")

</div>

> ggml : x2 speed for WASM by optimizing SIMD.  
> PR by Xuan-Son Nguyen for `llama.cpp`: \> This PR provides a big jump in speed for WASM by leveraging SIMD instructions for `qX_K_q8_K` and `qX_0_q8_0` dot product functions. \> \> …

Read in full here:

> **[ggml : x2 speed for WASM by optimizing SIMD](https://simonwillison.net/2025/Jan/27/llamacpp-pr/)**
>
> PR by Xuan-Son Nguyen for \`llama.cpp\`: \> This PR provides a big jump in speed for WASM by leveraging SIMD instructions for \`qX\_K\_q8\_K\` and \`qX\_0\_q8\_0\` dot product functions. \> \> …

_This thread was posted by one of our members via one of our news source trackers._