Repository navigation
Conversation
Introduce a separate gfx1200/gfx1201 backend with wave32 HIP inference primitives, Hugging Face attention/norm integration, portable generation, serving and serial benchmarks. Preserve the CUDA path and reject unsupported native-engine features explicitly. Add per-source host profiling, HIP/CUDA current-stream event spans, a 256-operation instrumentation floor and CPU/RAM/GPU/VRAM telemetry. Include portable packaging, documented ISA design/support boundaries, isolated tests and CPU/optional RDNA4 CI. Validation: 106 CPU/API tests passed with Transformers 4.51.3 and 4.57.1; 145 all-dtype CPU checks passed; pure ROCm wheel and launcher smoke checks passed. Four native GPU tests skipped. Native HIP compilation and hardware qualification remain for the target system. Signed-off-by: Maxritz <7871167+Maxritz@users.noreply.github.com> Co-authored-by: arena-agent <297053741+arena-agent@users.noreply.github.com>
Preserve static public exports and the StrictBaseModel compatibility alias while applying the configured legacy formatters. Bind portable serving to loopback by default and share tokenizer special-token configuration so Bandit passes without new suppressions. Add regression tests, update the architecture and contributor guidance, tighten resolved legacy lint counts, and disclose the dependency review findings. Signed-off-by: Maxritz <7871167+Maxritz@users.noreply.github.com>
Maxritz
requested review from
QiJune,
ZhanruiSunCh,
asfiyab-nvidia,
brnguyen2,
chang-l,
kaiyux,
mikeiovine and
tburt-nv
October 8, 2026 09:57
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.