metal: Cache compiled library at device level #12265
Merged
Conversation
This file contains hidden or 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
github-actions
bot
added
ggml
BB-fat
force-pushed
the
metal-library-cache
branch
2 times, most recently
from
6b3a511 to
0569909
Compare
Contributor
Author
|
During testing, I found an objc double-release issue, I am trying to fix it. |
BB-fat
force-pushed
the
metal-library-cache
branch
from
0569909 to
70432c7
Compare
Contributor
Author
|
@ggerganov Please review when convenient. |
ggerganov
approved these changes
Mar 11, 2025
ishaangandhi
pushed a commit
to ishaangandhi/llama.cpp
that referenced
this pull request
Mar 12, 2025
jpohhhh
pushed a commit
to Telosnex/llama.cpp
that referenced
this pull request
Mar 14, 2025
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Mar 19, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Currently, Metal shaders are recompiled for every llama context initialization, which is redundant and impacts performance when creating multiple contexts.
Cache the compiled Metal library at the device context level (g_ggml_ctx_dev_main), reusing it for subsequent context initializations.
Fixes #12199