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

[V1][Misc] Avoid unnecessary log output (#13289)

Browse Source
This commit is contained in:
Jee Jee Li
2025-02-17 11:26:24 +08:00
committed by GitHub
parent 69e1d23e1e
commit 2010f04c17
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/v1/worker/gpu_model_runner.py
View File

@@ -96,11 +96,13 @@ class GPUModelRunner(LoRAModelRunnerMixin):
self.mm_registry = MULTIMODAL_REGISTRY
self.uses_mrope = model_config.uses_mrope
# NOTE: Initialized client is only used for processing dummy
# multimodal data into multimodal kwargs for GPU memory profiling.
# Only applicable to multimodal models with legacy input mapper.
self.mm_input_mapper_profiling = MMInputCacheClient(self.model_config)
self.mm_input_mapper_profiling.use_cache = False
if self.is_multimodal_model:
# NOTE: Initialized client is only used for processing dummy
# multimodal data into multimodal kwargs for GPU memory profiling.
# Only applicable to multimodal models with legacy input mapper.
self.mm_input_mapper_profiling = MMInputCacheClient(
self.model_config)
self.mm_input_mapper_profiling.use_cache = False
encoder_compute_budget, encoder_cache_size = compute_encoder_budget(
model_config=model_config,