Repository navigation
Conversation
Contributor
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
This was referenced Oct 20, 2026
Provide the Rust payload, group and scratch contracts, native CUB provider and Oxide integration with complete Block and Warp I/O. Signed-off-by: Trent Nelson <trent@trent.me>
tpn
force-pushed
the
codex/cuda-coop-rust-r01
branch
from
October 25, 2026 01:33
4fa55e6 to
53da492
Compare
tpn
changed the title
This was referenced Oct 25, 2026
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Rust kernels need typed cooperative payloads and a consistent route to CUB specialization. This adds ThreadData validity, CUDA groups and queries, temporary storage and typed reservations, the native provider and Oxide adapter, and complete Block and physical/logical Warp Load/Store algorithms. The examples and guide cover inference, in-place load, exact multidimensional launch shapes and explicit storage completion.
Uses the coordinated Oxide compiler in NVIDIA/cuda-rust#1589, pinned to
96caed46. The owning comparison is based directly onmain.Validation on the reconstructed layer: formatting, host tests, clippy and docs, native provider coverage and standalone public examples on CUDA 13.3 / sm_120; 227 Vectorize cases with memcheck, racecheck and synccheck; and 148 logical-Warp cases with memcheck. Historical broader diagnostics, sanitizer and profile evidence retains its original source attribution.
This PR remains draft.