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

[Multi Modal] Configurable MM Profiling (#25631)

Browse Source 
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Wenlong Wang
2025-10-03 03:59:10 -07:00
committed by GitHub
parent 2ed3f20dba
commit 79aa244678
60 changed files with 654 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/engine/arg_utils.py
View File

@@ -376,7 +376,7 @@ class EngineArgs:
quantization: Optional[QuantizationMethods] = ModelConfig.quantization
enforce_eager: bool = ModelConfig.enforce_eager
disable_custom_all_reduce: bool = ParallelConfig.disable_custom_all_reduce
limit_mm_per_prompt: dict[str, int] = \
limit_mm_per_prompt: dict[str, Union[int, dict[str, int]]] = \
get_field(MultiModalConfig, "limit_per_prompt")
interleave_mm_strings: bool = MultiModalConfig.interleave_mm_strings
media_io_kwargs: dict[str, dict[str,