Merge origin/main into dev/vllm-align

Resolved conflicts:
- vllm_omni/inputs/preprocess.py: took origin/main's elif mm_processor_kwargs branch, fixed undefined mm_uuids reference
- vllm_omni/model_executor/models/qwen3_tts/qwen3_tts_code_predictor_vllm.py: took origin/main's NPU support

Made-with: Cursor

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-03-02 02:10:32 +00:00
commit 26744bcb35
240 files changed
+25869 -3091

No files matched your search

+24 -3
View File
@@ -31,17 +31,36 @@ class OmniInputPreprocessor(InputPreprocessor):
parsed_content: OmniTextPrompt,
tokenization_kwargs: dict[str, Any] | None = None,
) -> OmniTokenInputs | MultiModalInputs:
"""Process text prompts with support for mm_processor_kwargs.
Extends base class to support mm_processor_kwargs without multi_modal_data.
This is needed for models like GLM-Image where text-to-image generation
requires processor kwargs (target_h, target_w) to format the prompt.
"""
prompt_text = parsed_content["prompt"]
mm_processor_kwargs = parsed_content.get("mm_processor_kwargs") or {}
inputs: OmniTokenInputs | MultiModalInputs
if multi_modal_data := parsed_content.get("multi_modal_data"):
inputs = self._process_multimodal(
prompt_text,
multi_modal_data,
parsed_content.get("mm_processor_kwargs") or {},
mm_processor_kwargs,
tokenization_kwargs=tokenization_kwargs,
)
prompt_embeds = parsed_content.get("prompt_embeds")
if prompt_embeds is not None:
inputs["prompt_embeds"] = prompt_embeds
additional_information = parsed_content.get("additional_information")
if additional_information is not None:
inputs["additional_information"] = additional_information
elif mm_processor_kwargs:
inputs = self._process_multimodal(
prompt_text,
{},
mm_processor_kwargs,
tokenization_kwargs=tokenization_kwargs,
)
else:
prompt_token_ids = self._tokenize_prompt(
prompt_text,
@@ -72,8 +91,10 @@ class OmniInputPreprocessor(InputPreprocessor):
prompt_embeds = parsed_content.get("prompt_embeds")
additional_information = parsed_content.get("additional_information")
multi_modal_data = parsed_content.get("multi_modal_data")
inputs: OmniTokenInputs | MultiModalInputs
if multi_modal_data := parsed_content.get("multi_modal_data"):
if multi_modal_data:
inputs = self._process_multimodal(
prompt_token_ids,
multi_modal_data,