forked from ggerganov/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Avoid using saved CUDA graph if scale changes
Fixes ggerganov#9451
- Loading branch information
Showing
2 changed files
with
17 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
GGML_MAX_OP_PARAMS
is the size of theop_params
field in bytes, not 32-bit integers, so this will cause an overflow. I would suggest using a plainmemcpy
andmemcmp
to copy and compare this field, since it is intended to be used a generic storage buffer by the ops that need additional parameters.