llama.cpp
cuda : Use byte strides for roll to allow non-contiguous ROLL operations
#29547
Merged

cuda : Use byte strides for roll to allow non-contiguous ROLL operations #29547

bertaye
bertaye cuda : Use byte strides for roll to allow non-contiguous ROLL operations
5328aa58
bertaye bertaye requested a review 50 days ago
github-actions github-actions added ggml
github-actions github-actions added CUDA
ggml-gh-bot
ggml-gh-bot ggml-gh-bot added draft
github-actions github-actions marked this pull request as draft 50 days ago
github-actions github-actions removed draft
bertaye bertaye marked this pull request as ready for review 49 days ago
JohannesGaessler
JohannesGaessler approved these changes on 2026-10-06
JohannesGaessler JohannesGaessler added merge ready
ggerganov ggerganov merged d8880160 into master 39 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone