biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-05-27 17:44:20 +09:00
committed by GitHub
parent 6881107948
commit a68e293cb9
37 changed files with 360 additions and 247 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/worker/utils.py
View File

@@ -10,7 +10,7 @@ def sanity_check_mm_encoder_outputs(
) -> None:
"""
Perform sanity checks for the result of
{meth}`vllm.model_executor.models.SupportsMultiModal.get_multimodal_embeddings`.
[`vllm.model_executor.models.SupportsMultiModal.get_multimodal_embeddings`][].
"""
assert isinstance(mm_embeddings, (list, tuple, torch.Tensor)), (
"Expected multimodal embeddings to be a list/tuple of 2D tensors, "
@@ -39,7 +39,7 @@ def scatter_mm_placeholders(
Scatter the multimodal embeddings into a contiguous tensor that represents
the placeholder tokens.
{class}`vllm.multimodal.processing.PromptUpdateDetails.is_embed`.
[`vllm.multimodal.processing.PromptUpdateDetails.is_embed`][].
Args:
embeds: The multimodal embeddings.