Skip to content

Pull requests: google/gemma.cpp

New pull request New
6 Open 706 Closed
6 Open 706 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention.
#835 opened Feb 13, 2026 by copybara-service bot Loading…
Support building with Emscripten copybara-import Trigger Copybara for merging pull requests
#833 opened Feb 12, 2026 by brendandahl Loading…
3
Fixes to activations and tensor params
#747 opened Oct 28, 2025 by copybara-service bot Loading…
[Feature] ISS-60: Implement Self Extend
#431 opened Oct 18, 2024 by jonpsy Loading…
3 of 5 tasks
31
Implement the matmul op with Onednn to leverage AMX optimization.
#413 opened Oct 8, 2024 by copybara-service bot Loading…
Add configurables for norm/rope/activation/scale/residual connection.
#287 opened Jul 3, 2024 by copybara-service bot Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.