kevin d60daca4a8 [Feature] consider multimodal model when dummy run (#6045) ...

* add mm do profile

* updata code

* update code

* update code

* update code

* update test case

* update code

* update code

* fix xpu bug

* update code

* add mm do profile

* update test case

* update code

2026-02-09 17:49:55 +08:00

..

ernie4_5_vl_processor

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00

paddleocr_vl_processor

…

qwen3_vl_processor

[Models] Add Qwen3-VL Moe Model Support (#5913)

2026-01-08 11:36:42 +08:00

qwen_vl_processor

[Models] Qwen3VL and Qwen3VL-Moe CUDA graph Support (#5962)

2026-01-09 17:09:02 +08:00

v1

[Optimization] The pre- and post-processing pipeline do not perform dict conversion (#5494)

2026-01-22 00:50:52 +08:00

__init__.py

…

ernie4_5_processor.py

[Optimization]update prompt & prompt_token_ids (#6334)

2026-02-04 20:08:01 +08:00

ernie4_5_tokenizer.py

…

mm_data_processor.py

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00

preprocess.py

[Optimization] The pre- and post-processing pipeline do not perform dict conversion (#5494)

2026-01-22 00:50:52 +08:00

text_processor.py

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00

tokenzier_client.py

…

utils.py

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00