Prebuilt: drop the stale GGML_METAL_USE_BF16 define - #38
Merged
Conversation
…USE_BF16 define Pin #37 in pr-set.json: on macOS 14 VMs the Apple Paravirtual GPU returns stale data for mmap-backed weight buffers, so the patch makes the Metal backend stop advertising buffer_from_host_ptr there and llama.cpp falls back to copied weights (same path as --no-mmap). GGML_METAL_USE_BF16 no longer exists in current llama.cpp (bf16 is runtime-probed since the ggml-metal rewrite), so the define was a no-op; remove it from the macOS matrix entry.
GGML_METAL_USE_BF16 no longer exists as a build option in the current source tree (bf16 is runtime-probed), so passing it was a no-op. The macOS 14 paravirtual mmap pin moves to a separate decision.
danielhanchen
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Removes the stale
-DGGML_METAL_USE_BF16=ONdefine from the macOS arm64 prebuilt matrix.The option no longer exists in the current source tree: bf16 support is runtime-probed by ggml (
has_bfloatviasupportsFamily:checks inggml-metal-device.m, with theGGML_METAL_BF16_DISABLEenv override). Passing the define was a no-op CMake cache variable, so this changes nothing in the produced binaries; it only stops passing a flag CMake ignores.Not included
The macOS 14 paravirtual mmap fix (PR #37) is intentionally not pinned here; whether to carry that patch is a separate decision. Until then, macOS 14 virtual machines (GitHub macos-14 runners) keep the known mmap staleness quirk with large models; bare metal Macs are unaffected.
Verification