Repository navigation
Automatically load compiled CG Output IR without recompiling - #1519
Merged
Qiong Wu (qiowu) (DingmaomaoBJTU) merged 3 commits intoNov 5, 2026
Conversation
Qiong Wu (qiowu) (DingmaomaoBJTU)
requested a review
from a team
as a code owner
November 5, 2026 08:47
Qiong Wu (qiowu) (DingmaomaoBJTU)
force-pushed
the
codex/offline-dml-precompiled-load
branch
from
November 5, 2026 08:52
51160a4 to
f404377
Compare
Zhenchao Ni (zhenchaoni)
approved these changes
Nov 5, 2026
Yue Sun (KayMKM)
approved these changes
Nov 5, 2026
Qiong Wu (qiowu) (DingmaomaoBJTU)
merged commit Nov 5, 2026
607d7bd
into
microsoft:main
9 checks passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Offline DML CG Output IR can fail with 0x80070032 when WinMLRuntimeSession sends an already compiled artifact through the compiler again, even though CLI compilation and reload validation succeeded.
Detect Output IR internally by parsing the top-level module interface attribute through the MLIR C API. A cgc_output interface loads directly into the Runtime pipeline; Input IR and ONNX retain the existing compilation path. Both text and bytecode artifacts are supported, without scanning filenames/comments or adding a public API flag. Classification happens before loading the Runtime model to avoid leaking native handles if parsing fails.
Validation:
Rebased on upstream main d7055f9. The original RTX 5090 D benchmark roster has not been rerun. No caller/API changes are required for Output IR detection.