Open
Conversation
Add ldconfig for nvidia/tensorrt .so paths, prune large site-packages dirs from ldd scan to speed up build. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Switch from torchscript-based TRT compilation to torch_tensorrt.compile with ExportedProgram (.ep) format. Add GPU memory cleanup, improve error handling with fallback to eager mode. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Make tensorrt semaphore optional with a default count, so existing specs without it don't break. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
supersergiy
approved these changes
Mar 25, 2026
trivoldus28
reviewed
Mar 25, 2026
| assert input_shape is not None # mypy | ||
|
|
||
| trt_fname = ( | ||
| str(xxhash.xxh128(str((path, tuple(input_shape))).encode("utf-8")).hexdigest()) |
Contributor
There was a problem hiding this comment.
I think you need to also add the gpu model or gpu capability to the hash. I'm not sure if a T4 can run a model compiled by L4 or reversed
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1205 +/- ##
==========================================
- Coverage 99.98% 99.97% -0.01%
==========================================
Files 192 192
Lines 10199 10214 +15
==========================================
+ Hits 10197 10211 +14
- Misses 2 3 +1 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Occasionally it looks like the workers will fail to find TensorRT, but it's handled gracefully.