[BE] Rename should_torch_compile_mm_vit to should_torch_compile_mm_encoder (#36281)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
This commit is contained in:
@@ -26,7 +26,7 @@ This feature is off by default, but can be enabled by setting `compile_mm_encode
|
||||
|
||||
To compile a multimodal component such as an encoder, we follow the same mechanism as the LLM text backbone, with a few additional scaffoldings:
|
||||
|
||||
1. The `@support_torch_compile` decorator should include `enable_if=should_torch_compile_mm_vit`. This will gate the compilation behind our
|
||||
1. The `@support_torch_compile` decorator should include `enable_if=should_torch_compile_mm_encoder`. This will gate the compilation behind our
|
||||
`compile_mm_encoder` configuration
|
||||
|
||||
2. `with set_model_tag("<component_name>", is_encoder=True)` context manager should be used around the nn.Module's instantiation. Since torch.compile
|
||||
|
||||
Reference in New Issue
Block a user