Add support for batching (take two) #270
Merged
Conversation
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
Add support for inspection and eviction to queue Mock run info batching Mock run info batching Make TF tests work Add batching for ONNX and ONNX-ML Fix torch API, still WIP Fix torch backend Fixes after rebasing Add auto-batching to TFLite backend Fix from rebase Add batching args to command and change API accordingly Add batching heuristics [WIP] Fix TFLite test by accessing first tensor in first batch safely Temporarily comment out wrong_bg test check Implement batching heuristics Introduce autobatch tests, tflite still fails Fix segfault when error was generated from the backend Fix tflite autobatch test Updated documentation with auto batching Remove stale comments Avoid making extra copies of inputs and outputs when batch count is 1 Address review comments re const-correctness Add tests to detect failures Fix slicing and concatenation Fix tensor slicing and concatenating Temporarily disable tflite autobatch test due to tflite limitation Disable support for autobatching for TFLITE
Codecov Report
@@ Coverage Diff @@
## master #270 +/- ##
==========================================
+ Coverage 53.28% 55.79% +2.51%
==========================================
Files 25 25
Lines 4634 5022 +388
==========================================
+ Hits 2469 2802 +333
- Misses 2165 2220 +55
Continue to review full report at Codecov.
|
|
Todo:
|
|
Valgrind looks legit, I can't reproduce the crash anymore. |
|
@filipecosta90 @hhsecond ready for review/approval |
* test cases for crash test * Fix issue with evict. Port test to multiprocessing to allow killing pending command. * Use terminate instead of kill Co-authored-by: Luca Antiga <[email protected]>
|
I fixed a last (embarassing) bug in queue eviction (#310). |
lantiga
added a commit
that referenced
this pull request
May 6, 2020
Add support for batching (take two) (#270) * Add support for automated batching Add support for inspection and eviction to queue Mock run info batching Mock run info batching Make TF tests work Add batching for ONNX and ONNX-ML Fix torch API, still WIP Fix torch backend Fixes after rebasing Add auto-batching to TFLite backend Fix from rebase Add batching args to command and change API accordingly Add batching heuristics [WIP] Fix TFLite test by accessing first tensor in first batch safely Temporarily comment out wrong_bg test check Implement batching heuristics Introduce autobatch tests, tflite still fails Fix segfault when error was generated from the backend Fix tflite autobatch test Updated documentation with auto batching Remove stale comments Avoid making extra copies of inputs and outputs when batch count is 1 Address review comments re const-correctness Add tests to detect failures Fix slicing and concatenation Fix tensor slicing and concatenating Temporarily disable tflite autobatch test due to tflite limitation Disable support for autobatching for TFLITE * Fix TFLite and tests after rebase * Temporarily disable macos CI build * Add synchronization to autobatch tests * Add synchronization to autobatch thread * Add synchronization to autobatch thread * Batching crashtest (#310) * test cases for crash test * Fix issue with evict. Port test to multiprocessing to allow killing pending command. * Use terminate instead of kill Co-authored-by: Luca Antiga <[email protected]> Co-authored-by: Sherin Thomas <[email protected]>
tnachen
reviewed
May 12, 2020
| status = ort->GetAllocatorWithDefaultOptions(&allocator); | ||
| if (status != NULL) { | ||
| goto error; | ||
| return NULL; |
There was a problem hiding this comment.
Is there a reason returning a status is ignored but line 437 it isn't?
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 reopens #241, which was merged and then reverted.
Issues not covered by tests emerged and need to be resolved before we merge again.
Details will follow here.