Conversation
Fix the following error that occurred when loading the extension: Error: dlopen(./dist/ai.dylib, 0x000A): symbol not found in flat namespace '_ggml_backend_blas_reg' Updated the Makefile to link against libggml-blas.a and include -lggml-blas in LDFLAGS for macOS builds. This enables BLAS support, potentially improving performance on macOS platforms.
Added checks to ensure a valid context exists before proceeding in llm_chat_check_context and llm_chat_create. This prevents misuse by requiring llm_context_create to be called prior to llm_chat_create, improving error handling and robustness.
…r for both make and make test Eliminates the inclusion of libggml-blas.a and its linker flag from the macOS build configuration in the Makefile. This streamlines the build process and avoids unnecessary dependencies for macOS targets. Usage example: export the following env var to use them both for make and make test: LLAMA="-DGGML_NATIVE=OFF -DGGML_METAL=ON -DGGML_ACCELERATE=ON -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=Apple" WHISPER="-DWHISPER_COREML=ON -DWHISPER_COREML_ALLOW_FALLBACK=ON" SQLITE3=/opt/homebrew/Cellar/sqlite/3.50.4/bin/sqlite3
danielebriggi
approved these changes
Nov 11, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added checks to ensure a valid context exists before proceeding in llm_chat_check_context and llm_chat_create. This prevents misuse by requiring llm_context_create to be called prior to llm_chat_create, improving error handling and robustness.