OpenVINO Backend: Upgrade graph cache to use n_leaves, node_idx, src_idx, and node type - #321
Open
mostafafaheem wants to merge 1 commit into
Open
mostafafaheem wants to merge 1 commit into
mostafafaheem wants to merge 1 commit into
Conversation
Collaborator
Author
|
@cavusmustafa I tried submitting this PR to your branch but the diff was messy because the forks are out of sync, so feel free to cherry pick if you agree with this approach. I thought it would be more robust than buffer addresses used in #261. |
ravi9
force-pushed
the
dev_backend_openvino
branch
from
September 17, 2026 17:37
40a2a96 to
972d231
Compare
mostafafaheem
force-pushed
the
cache
branch
2 times, most recently
from
September 19, 2026 10:24
6b572e4 to
4fbbf0b
Compare
mostafafaheem
force-pushed
the
cache
branch
from
September 19, 2026 10:28
4fbbf0b to
eaa2677
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Adds graph cache fields:
1. input_srcs: "<node_idx>:<src_idx>:<op_type>"
2. n_leaves
Instead of tensor names, this also avoids an O(n_nodes^2) loop (
std::find(node_names.begin(), node_names.end(), src_name)inside aforloop)Additional information
Replaces #261
Requirements