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

[VLM] Merged multi-modal processor for InternVL-based models (#12553)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Cyrus Leung
2025-02-04 16:44:52 +08:00
committed by GitHub
parent 96b23621c1
commit d1ca7df84d
34 changed files with 1469 additions and 1021 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/models/deepseek_vl2.py
View File

@@ -165,7 +165,11 @@ class DeepseekVL2ProcessingInfo(BaseProcessingInfo):
image_width=x[1], image_height=x[0]))
return ImageSize(width=width, height=height)
def get_mm_max_tokens_per_item(self, seq_len: int) -> Mapping[str, int]:
def get_mm_max_tokens_per_item(
self,
seq_len: int,
mm_counts: Mapping[str, int],
) -> Mapping[str, int]:
max_image_size = self.get_image_size_with_most_features()
max_image_tokens = self.get_num_image_tokens(
image_height=max_image_size.height,