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

[Docs] Fix warnings in mkdocs build (continued) (#24791)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-09-13 16:13:44 +09:00
committed by GitHub
parent 5febdc8750
commit 9a8966bcc2
27 changed files with 102 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/llava_next.py
View File

@@ -535,8 +535,9 @@ class LlavaNextForConditionalGeneration(nn.Module, SupportsMultiModal,
Args:
input_ids: Flattened (concatenated) input_ids corresponding to a
batch.
pixel_values: The pixels in each grid patch for each input image.
image_sizes: The original `(height, width)` for each input image.
positions: Position indices for the input tokens.
intermediate_tensors: Intermediate tensors from prior forward pass.
inputs_embeds: Optional tensor of input embeddings.
Info:
[LlavaNextImageInputs][]