Enable chunked prefill by default for supported execution providers - #939
Open
baijumeswani wants to merge 1 commit into
Open
Enable chunked prefill by default for supported execution providers#939baijumeswani wants to merge 1 commit into
baijumeswani wants to merge 1 commit into
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. |
| case ExecutionProvider::kTensorRT_RTX: | ||
| case ExecutionProvider::kWebGPU: | ||
| case ExecutionProvider::kCPU: | ||
| gen_params.SetSearchOption("chunk_size", kDefaultChunkSize); |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.