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

[Docs] add __init__.py to vllm/model_executor/layers/quantization/compressed_tensors/transform (#24974)

Browse Source 
Signed-off-by: samzong <samzong.lu@gmail.com>
This commit is contained in:
samzong
2025-09-20 02:32:27 +08:00
committed by GitHub
parent 2506ce5189
commit 138f0d1e75
5 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -527,7 +527,8 @@ class LlavaNextForConditionalGeneration(nn.Module, SupportsMultiModal,
Unlike in LLaVA-1.5, the number of image tokens inputted to the language
model depends on the original size of the input image. Including the
original image token in the input, the required number of image tokens
is given by [get_llava_next_image_feature_size][].
is given by [`LlavaNextProcessingInfo.get_num_image_tokens`][vllm.\
model_executor.models.llava_next.LlavaNextProcessingInfo.get_num_image_tokens].
This way, the `positions` and `attn_metadata` are consistent
with the `input_ids`.
@@ -540,7 +541,7 @@ class LlavaNextForConditionalGeneration(nn.Module, SupportsMultiModal,
inputs_embeds: Optional tensor of input embeddings.
Info:
[LlavaNextImageInputs][]
[`LlavaNextImageInputs`][vllm.model_executor.models.llava_next.LlavaNextImageInputs]
"""
if intermediate_tensors is not None:
inputs_embeds = None