cuBLAS doc + error if -ngl > 0 and no cuBLAS #1466
Closed
Conversation
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
JohannesGaessler
added
the
documentation
Green-Sky
reviewed
May 15, 2023
ggerganov
approved these changes
May 15, 2023
JohannesGaessler
force-pushed
the
cublas-documentation
branch
from
e4c0147 to
9b1f955
Compare
|
The log for the failed job says: So it looks like it has nothing to do with my changes? |
|
Looks like a temporary issue. I'm rerunning the failed jobs, should fix it. |
|
Which button would I have had to press to re-run the job myself? |
|
click on the jobs details and then in the upper right there is a re-run button. If something fails, you can also select re-run failed. :) |
|
Long since outdated. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds documentation for how to use the GPU accelerated token generation that I implemented. Also, if llama.cpp was compiled without cuBLAS and the user then tries to run llama.cpp with 1 or more gpu layers an arror is raised and informs the user that they need to compile with cuBLAS (this was a point of failure for multiple people).