[ExecuTorch][BE] Split kv cache and SDPA for better code sharing #27466
kimishpatellint.yml
on: pull_request
lintrunner
/
linux-job
8m 59s
android-java-format
/
linux-job
4m 0s
Annotations
1 error and 3 warnings
|
lintrunner / linux-job
Process completed with exit code 1.
|
|
FLAKE8 F401:
pytorch/executorch/examples/models/llama/source_transformation/sdpa.py#L12
'typing.Union' imported but unused
See https://www.flake8rules.com/rules/F401.html.
|
|
FLAKE8 F401:
pytorch/executorch/examples/models/llama/source_transformation/sdpa.py#L17
'executorch.examples.models.llama.source_transformation.quantized_kv_cache.QuantizedKVCache' imported but unused
See https://www.flake8rules.com/rules/F401.html.
|
|
FLAKE8 F401:
pytorch/executorch/extension/llm/export/test_export_passes.py#L1
'os' imported but unused
See https://www.flake8rules.com/rules/F401.html.
|