apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 17:11:21 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

[DataProcessor] Refactor multimodal processor: extract encoding strategies and unify MM processing pipeline (#7298)

Browse Source 
* merge mm processor
This commit is contained in:
luukunn
2026-04-15 19:01:06 +08:00
committed by GitHub
parent a218d29488
commit 3f84d8d893
36 changed files with 4016 additions and 681 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/input/ernie4_5_vl_processor/process.py
+2
View File
@@ -539,6 +539,7 @@ class DataProcessor(MMBaseDataProcessor):
outputs["mm_positions"].append(ImagePosition(len(outputs["input_ids"]), num_tokens))
outputs["input_ids"].extend([self.image_patch_id] * num_tokens)
outputs["token_type_ids"].extend([IDS_TYPE_FLAG["image"]] * num_tokens)
outputs["num_input_image_tokens"] += num_tokens
_, h, w = meta["thw"]
pos_ids = self._compute_3d_positions(1, h, w, outputs["cur_position"])
@@ -605,6 +606,7 @@ class DataProcessor(MMBaseDataProcessor):
outputs["mm_positions"].append(ImagePosition(len(outputs["input_ids"]), num_tokens))
outputs["input_ids"].extend([self.image_patch_id] * num_tokens)
outputs["token_type_ids"].extend([IDS_TYPE_FLAG["video"]] * num_tokens)
outputs["num_input_video_tokens"] += num_tokens
outputs["image_type_ids"].extend([1] * t)
pos_ids = self._compute_3d_positions(t, h, w, outputs["cur_position"])