fix(rocm): correct runtime capability and resolution semantics - #34
Draft
nekomario28 wants to merge 1 commit into
Draft
fix(rocm): correct runtime capability and resolution semantics#34nekomario28 wants to merge 1 commit into
nekomario28 wants to merge 1 commit into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Review/delivery carrier for upstream FlashML-org#132
This PR is an upstream FlashML-org#132 correction carrier, not a merge target for this fork's diverged
main.Base
review/pr132-head-45417560is an immutable snapshot ofFlashML-org/FreeToken#132head45417560beeba896a9b0866e50154d2a7a320b8b. The head commitbbeb65e88201d23604bc6a4c489c881e686dd27ais its direct one-commit child.Corrections
libamdhip64.so.*numerically rather than lexically, sharing the selector across setup/build and JIT discovery.Focused regression coverage for the three contracts is included in the same commit.
Existing gfx1101 evidence
Previously validated after composition on RX 7800 XT / gfx1101 with PyTorch
2.11.0+rocm7.2, HIP7.2.26015, TVM-FFI0.1.13.post3:_pinned_tensor+_cpu_moebuild: PASSgit diff --check: PASSClaim boundary: focused runtime/build correctness only; no full model serving, NVIDIA parity, multi-GPU RCCL, RDNA4, or performance claim.
Delivery status
Preferred delivery is to the existing upstream FlashML-org#132 author branch/conversation, preserving contributor lineage. Direct cross-fork PR/comment delivery via the currently connected GitHub integration is blocked with
403 Resource not accessible by integration. This carrier keeps the exact minimal delta ready for an authorized GitHub/CLI path.