ci(gfx11): add gfx1152 to the multiarch ROCm build - #70
Merged
Conversation
gfx1152 is an RDNA3.5 (Strix) APU arch already handled by the device code (the RDNA3_5 macro in vendors/hip.h and the GGML_CUDA_CC_IS_RDNA3_5 range in common.cuh both cover 0x1152), but the build workflow never enabled it: it was absent from GPU_TARGETS and, worse, its rocBLAS/hipBLASLt Tensile DBs were being pruned out by drop_arches. Add gfx1152 to GPU_TARGETS, drop it from the prune list, and update the arch counts/release notes accordingly. Tensile DBs for gfx1152 are present in the 7.15 nightly, same as gfx1151. Co-Authored-By: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
RDNA3_5macro invendors/hip.hand theGGML_CUDA_CC_IS_RDNA3_5range incommon.cuhboth cover0x1152). The gap was build-only:gfx1152was missing fromGPU_TARGETS.gfx1152was indrop_arches, so its rocBLAS/hipBLASLt Tensile DBs were being pruned out of the package.GPU_TARGETS, remove it from the prune list, update arch counts and release notes.Test plan