Skip to content

add hardware fp16_to_fp32 - #27452

Open
lexasub wants to merge 2 commits into
ggml-org:masterfrom
lexasub:misc
Open

add hardware fp16_to_fp32 #27452
lexasub wants to merge 2 commits into
ggml-org:masterfrom
lexasub:misc

Conversation

@lexasub

@lexasub lexasub commented Aug 20, 2026

Copy link
Copy Markdown
Contributor

Overview

Small changes - remove wasting time for fill vector, add hardware fp16_to_fp32 (small change, compiler will optimize dequantize_row_q4_0 better)

Additional information

Extracted from #27396 for fast review and merge small changes

Requirements

@lexasub
lexasub requested a review from ggerganov as a code owner August 20, 2026 17:42
@github-actions github-actions Bot added the ggml changes relating to the ggml tensor library for machine learning label Aug 20, 2026
@ggml-gh-bot

ggml-gh-bot Bot commented Aug 20, 2026

Copy link
Copy Markdown

Hi @lexasub, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

  • Multiple open PRs from a new contributor: We limit new contributors (those without a previously merged PR) to 1 open PR at a time. You currently have 3 open PRs.

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.

@lexasub

lexasub commented Aug 20, 2026

Copy link
Copy Markdown
Contributor Author

@slaren review pls, ok?

Comment thread src/llama-batch.cpp
udata->embd.clear();
udata->embd.reserve(n_embd_all);
} else {
udata->embd.resize(n_embd_all); // fill all size..new_size elems by 0.0f

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

guaranted save prev code logic - always alloc n_embd_all and fill 0.0f when batch.embd doesn't present

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant