[Model] Fix cached buffer allocation and fix dynamic shape in Phi3v #3082
Conversation
This file contains 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
This PR fixes the cached buffer allocation for larger new images and supports dynamic shapes in the vision encoder.
|
Hi @MasterJH5574 , could you take a look, thanks. |
MasterJH5574
reviewed
Jan 4, 2025
There was a problem hiding this comment.
Overall looks good! Thank you @mengshyu, Just left one minor nit.
cpp/support/vlm_utils.h
Outdated
Comment on lines
23
to
43
| void CalculateResizeShape(tvm::runtime::NDArray image_data, std::string model_type, | ||
| int& target_height, int& target_width); | ||
| /*! | ||
| * \brief Calculate the padding height and width for an image based on the input data and model | ||
| * type. \param image_data The input image data as a TVM NDArray. \param model_type The type of the | ||
| * model influencing the padding parameters (e.g., phi3v). \param pad_height Reference to the | ||
| * variable where the calculated padding height will be stored. \param pad_width Reference to the | ||
| * variable where the calculated padding width will be stored. | ||
| */ | ||
| void CalculatePadShape(tvm::runtime::NDArray image_data, std::string model_type, int& pad_height, | ||
| int& pad_width); | ||
|
|
||
| /*! | ||
| * \brief Calculate the cropping height and width for an image based on the input data and model | ||
| * type. \param image_data The input image data as a TVM NDArray. \param model_type The type of the | ||
| * model influencing the cropping parameters (e.g., phi3v). \param crop_height Reference to the | ||
| * variable where the calculated cropping height will be stored. \param crop_width Reference to the | ||
| * variable where the calculated cropping width will be stored. | ||
| */ | ||
| void CalculateCropShape(tvm::runtime::NDArray image_data, std::string model_type, int& crop_height, | ||
| int& crop_width); |
There was a problem hiding this comment.
A minor nit for convention: let's avoid passing mutable reference and instead pass pointers for functions here. For example,
void CalculateCropShape(tvm::runtime::NDArray image_data, std::string model_type, int* crop_height,
int* crop_width);
MasterJH5574
approved these changes
Jan 5, 2025
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.
This PR fixes the cached buffer allocation for larger new images and supports dynamic shapes in the vision encoder.