Enable chunked prefill by default for supported execution providers - #939
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
There was a problem hiding this comment.
Pull request overview
Enables a default chunked-prefill size for selected execution providers.
Changes:
- Adds CPU provider-name recognition.
- Passes execution-provider context into search-option handling.
- Adds tests for defaults, overrides, and provider resolution.
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
execution_provider_test.cc |
Tests CPU provider aliases. |
search_options_test.cc |
Tests chunk-size behavior. |
search_options.h |
Extends the search-options interface. |
search_options.cc |
Applies provider-specific chunk defaults. |
onnx_chat_generator.cc |
Supplies the model execution provider. |
execution_provider.h |
Recognizes CPU provider names. |
baijumeswani
changed the base branch from
main
to
baijumeswani/upgrade-packages
August 3, 2026 16:34
Collaborator
Author
|
/azp run |
|
Azure Pipelines: 2 pipeline(s) were filtered out due to trigger conditions. |
xiaoyu-work
previously approved these changes
Aug 3, 2026
baijumeswani
force-pushed
the
baijumeswani/upgrade-packages
branch
from
August 3, 2026 21:44
aadad67 to
ec9e87e
Compare
baijumeswani
force-pushed
the
baijumeswani/chunked-prefill
branch
from
August 3, 2026 21:44
54f5c2a to
d51cee3
Compare
Collaborator
Author
|
/azp run |
|
Azure Pipelines: 2 pipeline(s) were filtered out due to trigger conditions. |
bmehta001
previously approved these changes
Aug 3, 2026
baijumeswani
force-pushed
the
baijumeswani/upgrade-packages
branch
from
August 4, 2026 00:46
ec9e87e to
e8e163d
Compare
baijumeswani
force-pushed
the
baijumeswani/chunked-prefill
branch
from
August 4, 2026 00:46
d51cee3 to
39a9742
Compare
baijumeswani
force-pushed
the
baijumeswani/upgrade-packages
branch
from
August 4, 2026 15:06
11f6146 to
4d37878
Compare
baijumeswani
force-pushed
the
baijumeswani/chunked-prefill
branch
from
August 4, 2026 15:06
39a9742 to
58b827b
Compare
baijumeswani
force-pushed
the
baijumeswani/chunked-prefill
branch
from
August 4, 2026 16:54
58b827b to
31d85c5
Compare
baijumeswani
force-pushed
the
baijumeswani/chunked-prefill
branch
from
August 4, 2026 18:59
31d85c5 to
f7b39c2
Compare
bmehta001
previously approved these changes
Aug 4, 2026
baijumeswani
enabled auto-merge (squash)
August 4, 2026 19:10
bmehta001
approved these changes
Aug 4, 2026
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.
Sets the ORT GenAI
chunk_sizesearch option to 2048 by default for CPU, CUDA, Nv TensorRT RTX, and WebGPU.Existing positive
chunk_sizevalues are preserved. Missing or zero values use the new default, while ORT GenAI determines whether the model supports chunked prefill. Tests cover provider selection and override behavior.