Skip to content

append_projected_kv fusion - #665

Merged
CC-Yeh merged 3 commits into
mainfrom
dflash_improvements2
Jul 31, 2026
Merged

append_projected_kv fusion#665
CC-Yeh merged 3 commits into
mainfrom
dflash_improvements2

Conversation

@CC-Yeh

@CC-Yeh CC-Yeh commented Jul 30, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor
  • Fuse many small GEMMs into one bigger GEMM
  • Cleanup QKVNorm kernels and unused types

Requires: trymirai/lalamo#330

@CC-Yeh

CC-Yeh commented Jul 30, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

10-50% (accepted 6-16 tokens) faster than old append_kv

@CC-Yeh CC-Yeh changed the title append_projection_kv fusion append_projected_kv fusion Jul 30, 2026
@CC-Yeh
CC-Yeh marked this pull request as ready for review July 30, 2026 14:26
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Jul 30, 2026

Copy link
Copy Markdown

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

@CC-Yeh CC-Yeh mentioned this pull request Jul 30, 2026
Merged
@CC-Yeh
CC-Yeh enabled auto-merge (squash) July 31, 2026 00:45
@CC-Yeh

CC-Yeh commented Jul 31, 2026

Copy link
Copy Markdown
Contributor Author

@codex review

chatgpt-codex-connector[bot]
chatgpt-codex-connector Bot reviewed Jul 31, 2026
View reviewed changes

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cbefb2373c

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread crates/backend-uzu/src/encodable_block/dflash.rs
Comment thread crates/backend-uzu/src/encodable_block/dflash.rs
Comment thread crates/backend-uzu/src/encodable_block/dflash.rs
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Jul 31, 2026

Copy link
Copy Markdown

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

@CC-Yeh
CC-Yeh merged commit 702c172 into main Jul 31, 2026
7 checks passed
@CC-Yeh
CC-Yeh deleted the dflash_improvements2 branch July 31, 2026 08:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@chatgpt-codex-connector chatgpt-codex-connector[bot] chatgpt-codex-connector[bot] left review comments
@eugenebokhan eugenebokhan eugenebokhan approved these changes
@uuuvn uuuvn Awaiting requested review from uuuvn uuuvn is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@CC-Yeh @eugenebokhan