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

12
vllm/model_executor/models/qwen.py
View File

@@ -779,7 +779,11 @@ class QWenVLProcessingInfo(BaseProcessingInfo):
def get_supported_mm_limits(self) -> Mapping[str, Optional[int]]:
return {"image": None}
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]:
return {"image": self.get_num_image_tokens()}
def get_num_image_tokens(self) -> int:
@@ -799,13 +803,13 @@ class QWenVLDummyInputsBuilder(BaseDummyInputsBuilder[QWenVLProcessingInfo]):
vision_config = hf_config.visual
max_image_size = vision_config["image_size"]
target_width = target_height = vision_config["image_size"]
num_images = mm_counts.get("image", 0)
mm_data = {
"image":
self._get_dummy_images(width=max_image_size,
height=max_image_size,
self._get_dummy_images(width=target_width,
height=target_height,
num_images=num_images)
}