-
Notifications
You must be signed in to change notification settings - Fork 14
Issues: NVIDIA/TensorRT-Incubator
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Incorrect broadcast elimination when both operands to elementwise are broadcasted
mlir-tensorrt
Pull request for the mlir-tensorrt project
#521
opened Feb 21, 2025 by
pranavm-nvidia
No-op slices cause executables to drop outputs
mlir-tensorrt
Pull request for the mlir-tensorrt project
#496
opened Feb 12, 2025 by
pranavm-nvidia
[mlir-tensorrt] Enhancement: Support splat dense attributes for TRT plugins
#491
opened Feb 7, 2025 by
samurdhikaru
MHA kernels not triggered in nanoGPT sample
mlir-tensorrt
Pull request for the mlir-tensorrt project
performance
#464
opened Dec 18, 2024 by
yizhuoz004
Potential eager cache False Positive hits due to floating point strings
#448
opened Dec 16, 2024 by
farazkh80
Stride validation fails for empty tensor input
mlir-tensorrt
Pull request for the mlir-tensorrt project
#398
opened Nov 21, 2024 by
parthchadha
Incorrect quantize output with fp16 scales
mlir-tensorrt
Pull request for the mlir-tensorrt project
#392
opened Nov 19, 2024 by
parthchadha
[mlir-tensorrt] TensorRT Dialect New feature or request
mlir-tensorrt
Pull request for the mlir-tensorrt project
ReifyRankedShapedTypeOpInterface
implementation
enhancement
#369
opened Nov 13, 2024 by
christopherbate
nanoGPT FP8 compilation failed
mlir-tensorrt
Pull request for the mlir-tensorrt project
#353
opened Nov 8, 2024 by
yizhuoz004
Support collections of tensors as inputs to compiled functions
#343
opened Nov 6, 2024 by
pranavm-nvidia
Add support for multiple optimization profiles
tripy
Pull request for the tripy project
#315
opened Oct 28, 2024 by
parthchadha
dtype constraints does not work for overloaded functions
good first issue
Good for newcomers
#300
opened Oct 24, 2024 by
pranavm-nvidia
stablehlo-to-tensorrt
does not support converting stablehlo.dynamic_gather
mlir-tensorrt
#264
opened Oct 10, 2024 by
parthchadha
Concatenating a shape tensor using the
*
op does not work with fill
#207
opened Sep 16, 2024 by
pranavm-nvidia
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.