Adds some testing infrastructure and removes lots of deprecated options#11
Merged
ankan-ban merged 5 commits intoankan-ban:nv-tensorrt-rtx-epfrom Apr 23, 2025
Merged
Conversation
ankan-ban
reviewed
Apr 22, 2025
| if (exclude_ops_set.find(node->OpType()) != exclude_ops_set.end()) { | ||
| supported_node = false; | ||
| } | ||
| // Exclude contrib ops |
Owner
There was a problem hiding this comment.
Do we need this check? Doesn't the logic automatically exclude any op that TRT can't support?
I think the plan to support LLMs is to make use of GQA contrib op for some time and have TRT implement a plugin to support that - so this check may prevent that from working when TRT plugin is ready (or maybe that's not an issue?)
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No longer set options via env variables.
Add EP to default providers to test and add a native test that shows how to quick load a context file.
Remove implicit int8 quantization together with all precision bypasses besides strong typed ONNX.
Add default options for dynamic shapes.