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

[Core] Store only the keys for multi-modal data in P0 (#22198)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-07 16:45:04 +08:00
committed by GitHub
parent 289b18e670
commit 766bc8162c
17 changed files with 325 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
vllm/engine/arg_utils.py
View File

@@ -1230,17 +1230,17 @@ class EngineArgs:
enable_multimodal_encoder_data_parallel,
)
supports_mm_preprocessor_cache = (self.data_parallel_size == 1
or data_parallel_external_lb)
if (not supports_mm_preprocessor_cache
and model_config.is_multimodal_model
and not model_config.disable_mm_preprocessor_cache):
logger.warning(
"Multi-modal preprocessor cache is not compatible "
"with data parallelism when there does not exist a "
"one-to-one correspondance between API process and "
"EngineCore process, so the cache will be disabled.")
model_config.set_disable_mm_preprocessor_cache(True)
if model_config.is_multimodal_model:
dp_supports_mm_processor_cache = (self.data_parallel_size == 1
or data_parallel_external_lb)
if (not dp_supports_mm_processor_cache
and not model_config.disable_mm_preprocessor_cache):
logger.warning(
"Multi-modal processor cache is disabled because "
"it is not compatible with data parallelism when "
"there does not exist a one-to-one correspondance "
"between API and engine core processes.")
model_config.set_disable_mm_preprocessor_cache(True)
speculative_config = self.create_speculative_config(
target_model_config=model_config,