ollama 0.33.2 - #301407
Open
thypon wants to merge 1 commit into
Open
Conversation
Contributor
|
Thanks for your pull request. This has been closed because it appears to be missing the pull request template, perhaps because this was written by an AI not a human. We require humans to read and fill in these templates. Please edit this pull request to fill in the current pull request template. This workflow will reopen this pull request automatically once the template is complete. Do not open a new pull request for this. |
github-actions
Bot
added
the
go
SMillerDev
reviewed
Aug 31, 2026
Comment on lines
+70
to
+74
| # b10630: tools/tuning hardcodes CMAKE_SOURCE_DIR, which is the ollama | ||
| # build root under FetchContent; retarget to llama.cpp's own ggml-metal dir | ||
| inreplace llama_source_dir/"tools/tuning/CMakeLists.txt", | ||
| "${CMAKE_SOURCE_DIR}/ggml/src/ggml-metal", | ||
| "${CMAKE_CURRENT_SOURCE_DIR}/../../ggml/src/ggml-metal" |
Member
There was a problem hiding this comment.
When can this be removed? Is there an upstream issue or PR to follow?
Author
There was a problem hiding this comment.
No timeline, and I did not saw other reports, but I opened one ggml-org/llama.cpp#28114
8 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
HOMEBREW_NO_INSTALL_FROM_API=1 brew install --build-from-source <formula>?brew test <formula>?brew audit --strict <formula>(after doingHOMEBREW_NO_INSTALL_FROM_API=1 brew install --build-from-source ollama)? If this is a new formula, does it passbrew audit --new <formula>?AI disclosure: the PR was prepared using the opencode CLI (model: z-ai/glm-5.3-flash). I (thypon) reviewed and verified all changes:
brew style,brew audit --strict --online,HOMEBREW_NO_INSTALL_FROM_API=1 brew install --build-from-source ollama, andbrew test ollamawere run locally on arm64 macOS 26 (Apple M5 Max) and all pass; the MLX runner loadslibmlxc.dylib/libmlx.dyliband the server runs as 0.33.2. I will answer maintainer questions and review comments myself.Changes
v0.33.0→v0.33.2(both are plain git-tag builds, so onlytag:/revision:change).b10488→b10630, taken from upstreamLLAMA_CPP_VERSIONat v0.33.2.tools/tuninghardcodes${CMAKE_SOURCE_DIR}/ggml/src/ggml-metalin itstarget_include_directories. Under ollama's FetchContent consumption,CMAKE_SOURCE_DIRis the ollama build root, so the build fails withfatal error: 'ggml-metal-tuning.h' file not found. Added aninreplaceretargeting it to${CMAKE_CURRENT_SOURCE_DIR}/../../ggml/src/ggml-metal. Upstream llama.cpp master still has the same line, so there is no upstream fix to reference yet.