ANE-friendly static llama #30598
Triggered via pull request
February 20, 2025 22:12
metascroy
Status
Failure
Total duration
11m 26s
Artifacts
–
lint.yml
on: pull_request
lintrunner
/
linux-job
11m 18s
android-java-format
/
linux-job
4m 36s
Annotations
1 error and 3 warnings
|
lintrunner / linux-job
Process completed with exit code 1.
|
|
FLAKE8 F401:
pytorch/executorch/examples/apple/coreml/llama/run.py#L3
'multiprocessing.process' imported but unused
See https://www.flake8rules.com/rules/F401.html.
|
|
UFMT format:
pytorch/executorch/examples/apple/coreml/llama/llama_transformer.py#L1
Run `lintrunner -a` to apply this patch.
|
|
FLAKE8 TOR102:
pytorch/executorch/examples/apple/coreml/llama/export.py#L165
`torch.load` without `weights_only` parameter is unsafe. Explicitly set `weights_only` to False only if you trust the data you load and full pickle functionality is needed, otherwise set `weights_only=True`.
See .
|