-
Notifications
You must be signed in to change notification settings - Fork 3k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Tutorial for PyTorch models that use custom operators
documentation
improvements or additions to documentation; typically submitted using template
#8025
opened Jun 10, 2021 by
natke
Loading…
6 tasks
Documentation update - add back line about --skip_tests for reduced ops build.
documentation
improvements or additions to documentation; typically submitted using template
#10157
opened Dec 30, 2021 by
edgchen1
Loading…
Add the possibility to quantize MatMul per-tensor when per_channel=True
quantization
issues related to quantization
#12000
opened Jun 27, 2022 by
regisss
Loading…
[Python API] Invoke CopyDataToTensor() with contiguous array
#14049
opened Dec 22, 2022 by
hariharans29
Loading…
Run filtered unit tests for python package test pipelines for TRT EP due to significantly increased of test time
#14381
opened Jan 20, 2023 by
chilo-ms
Loading…
[CUDA] Improve BeamSearch op's performance (GPT-2 use-case )
#14489
opened Jan 31, 2023 by
hariharans29
Loading…
Sync on CUDA EP level stream only if really needed
#17770
opened Oct 3, 2023 by
hariharans29
Loading…
Refactor should_quantize method to use and operator
#17900
opened Oct 12, 2023 by
baskrahmer
Loading…
Migrate issue labeler workflow to issueLabeler.yml policy
#21659
opened Aug 7, 2024 by
sophies927
Loading…
Migrate stale bot workflow to updateStaleIssues.yml policy
#21660
opened Aug 7, 2024 by
sophies927
Loading…
use cuda12.1 to build ort instead of cuda11.8 to fix ci failure
#21667
opened Aug 8, 2024 by
zhijxu-MS
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.