-
Couldn't load subscription status.
- Fork 702
Fix incorrect kernel mappings in Cadence HiFi functions.yaml #15216
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
base: main
Are you sure you want to change the base?
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15216
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New Failures, 3 Cancelled Jobs, 3 Unrelated FailuresAs of commit be6e26c with merge base 98baab7 ( NEW FAILURES - The following jobs have failed:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@michaelmaitland has exported this pull request. If you are a Meta employee, you can view the originating Diff in D84865463. |
0b01e9e to
c2e7697
Compare
…#15216) Summary: Fixed two bugs in fbcode/executorch/backends/cadence/aot/functions_hifi.yaml: 1. cadence::quantize_per_tensor_asym16u was incorrectly mapped to impl::HiFi::quantize_per_tensor_asym16s_out instead of asym16u_out 2. cadence::dequantize_per_tensor_asym32s was incorrectly mapped to impl::HiFi::dequantize_per_tensor_asym16s_out instead of asym32s_out The second bug caused runtime failures when dequantizing 32-bit signed integer tensors, as the wrong function expecting 16-bit integers was called, resulting in "Unhandled input dtype" assertion failures. Differential Revision: D84865463
c2e7697 to
fd65df8
Compare
…#15216) Summary: Fixed two bugs in fbcode/executorch/backends/cadence/aot/functions_hifi.yaml: 1. cadence::quantize_per_tensor_asym16u was incorrectly mapped to impl::HiFi::quantize_per_tensor_asym16s_out instead of asym16u_out 2. cadence::dequantize_per_tensor_asym32s was incorrectly mapped to impl::HiFi::dequantize_per_tensor_asym16s_out instead of asym32s_out The second bug caused runtime failures when dequantizing 32-bit signed integer tensors, as the wrong function expecting 16-bit integers was called, resulting in "Unhandled input dtype" assertion failures. Differential Revision: D84865463
…#15216) Summary: Fixed two bugs in fbcode/executorch/backends/cadence/aot/functions_hifi.yaml: 1. cadence::quantize_per_tensor_asym16u was incorrectly mapped to impl::HiFi::quantize_per_tensor_asym16s_out instead of asym16u_out 2. cadence::dequantize_per_tensor_asym32s was incorrectly mapped to impl::HiFi::dequantize_per_tensor_asym16s_out instead of asym32s_out Differential Revision: D84865463
fd65df8 to
be6e26c
Compare
Summary:
Fixed two bugs in fbcode/executorch/backends/cadence/aot/functions_hifi.yaml:
The second bug caused runtime failures when dequantizing 32-bit signed integer tensors, as the wrong function expecting 16-bit integers was called, resulting in "Unhandled input dtype" assertion failures.
Differential Revision: D84865463