Repository navigation
[Do not merge] Pin onnxruntime-extensions to a build with PR 1136 - #2763
Draft
Yueqing Zhang (BoarQing) wants to merge 4 commits into
Draft
Yueqing Zhang (BoarQing) wants to merge 4 commits into
Yueqing Zhang (BoarQing) wants to merge 4 commits into
Conversation
CI test vehicle for ROCm/hip-ep, which applies OGA PR diffs on top of v0.17.0. Points the onnxruntime-extensions pin at 99fec2db plus the two commits of microsoft/onnxruntime-extensions#1136 (UTF-8 offset fix in the STL regex pre-tokenizer fallback), hosted on a fork until microsoft#1136 merges. Made-with: Cursor Co-Authored-By: Cursor <cursoragent@cursor.com>
Yueqing Zhang (BoarQing)
added a commit
to ROCm/hip-ep
that referenced
this pull request
Oct 20, 2026
microsoft/onnxruntime-genai#2763 (draft, not for merge) moves OGA's onnxruntime-extensions pin from 99fec2db to 99fec2db plus the two commits of microsoft/onnxruntime-extensions#1136, which Laguna's tokenizer needs. Made-with: Cursor Co-Authored-By: Cursor <cursoragent@cursor.com>
4 tasks done
Ming Wang (amd-mingw)
pushed a commit
to ROCm/hip-ep
that referenced
this pull request
Oct 21, 2026
## Summary Test PR, not for merge. It adds the onnxruntime-extensions tokenizer fix ([microsoft/onnxruntime-extensions#1136](microsoft/onnxruntime-extensions#1136)) to the Windows OGA build, so the CI package can run Laguna-XS 2.1 in Jenkins. The whole change is one entry in `OGA_PR_PATCHES`. ## Related issue or design - [microsoft/onnxruntime-extensions#1136](microsoft/onnxruntime-extensions#1136): the tokenizer fix. - [microsoft/onnxruntime-genai#2763](microsoft/onnxruntime-genai#2763): draft, not for merge. It moves OGA's onnxruntime-extensions pin to `99fec2db` plus the two #1136 commits, hosted on a fork until #1136 merges. - #1241: QMoE `router_weights` support, already on main. ## Why OGA 0.17 (with PRs 2685, 2691, 2705, 2712) pins onnxruntime-extensions `99fec2db`, which throws `invalid string_view position` when encoding a Laguna prompt that has a non-ASCII character before a newline. Both Jenkins prompts (`prompt_128.txt`, `prompt_2k.txt`) hit it. ## What `windows-deps.yml`: `OGA_PR_PATCHES` gains `2763`. Only the Windows OGA build changes. ## Test plan - I replayed the "Apply OGA PR patches" step locally on v0.17.0 with `2685 2691 2705 2712 2763`. All five applied, and the resulting ortx pin is the fork commit `c114ea9`. Its `bpe_utils.hpp` is byte-identical to the #1136 head. - A local OGA build with this onnxruntime-extensions fix encodes both Jenkins prompts. The token IDs match Hugging Face `tokenizers` exactly, apart from the BOS token that OGA omits by default. - With that OGA, #1241's `hipgpu.dll` and `enable_graph_capture: "0"`, Laguna completes both Jenkins prompts on gfx1151. Its 24-token greedy output on `prompt_128.txt` matches the ORT CPU EP. ## Notes for reviewers - Laguna still needs `"enable_graph_capture": "0"` in its AMDGPU provider options under OGA 0.17. That is a model-config change and is not part of this PR. - Once #1136 merges and OGA pins a commit containing it, replace 2763 with that OGA change and close 2763. ## Checklist - [x] The change is focused, or links a design/series explaining its scope. - [x] Relevant tests were added or updated and the results are documented. - [x] User-facing or design documentation was updated when needed. Not applicable for a CI test change. - [x] Substantial AI assistance is disclosed, and I reviewed and understand the result. Cursor prepared the OGA PR, this change and this description; validated as described above. Co-authored-by: Cursor <cursoragent@cursor.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
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.
Do not merge. This is a CI test vehicle and will be closed once microsoft/onnxruntime-extensions#1136 merges and OGA pins a commit that contains it.
ROCm/hip-ep builds OGA v0.17.0 plus a list of OGA PR diffs. This PR lets that build pick up microsoft/onnxruntime-extensions#1136, which fixes
invalid string_view positionin the STL regex pre-tokenizer fallback when a non-ASCII character precedes a newline. That is the case for Laguna-XS 2.1 prompts.The only change is the
onnxruntime_extensionsline incmake/deps.txt. It now points at a fork commit: the current pin99fec2dbplus the two #1136 commits, so nothing else in onnxruntime-extensions changes. The branch starts from the commit that set99fec2db, so the diff is that single line.Used by ROCm/hip-ep#1243.
AI assistance: Cursor prepared the branch and this description; I reviewed them.