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

[Frontend] User-provided uuids for medias in chat. (RFC #22044) (#23449)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Chenheli Hua
2025-09-08 06:42:20 -07:00
committed by GitHub
parent 03dd652c16
commit 01dfb5e982
8 changed files with 1079 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/entrypoints/llm.py
View File

@@ -796,7 +796,7 @@ class LLM:
# NOTE: _parse_chat_message_content_parts() currently doesn't
# handle mm_processor_kwargs, since there is no implementation in
# the chat message parsing for it.
conversation, mm_data = parse_chat_messages(
conversation, mm_data, mm_uuids = parse_chat_messages(
msgs,
model_config,
tokenizer,
@@ -826,6 +826,9 @@ class LLM:
if mm_data is not None:
prompt["multi_modal_data"] = mm_data
if mm_uuids is not None:
prompt["multi_modal_uuids"] = mm_uuids
if mm_processor_kwargs is not None:
prompt["mm_processor_kwargs"] = mm_processor_kwargs