Skip to content

GitLab

Unverified Commit 7c2749a4 authored by youkaichao's avatar youkaichao Committed by GitHub
Browse files

[misc] add start loading models for users information (#6670)

parent 729171ae
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/worker/model_runner.py
View file @ 7c2749a4
...@@ -677,6 +677,7 @@ class GPUModelRunnerBase(ModelRunnerBase[TModelInputForGPU]): ...@@ -677,6 +677,7 @@ class GPUModelRunnerBase(ModelRunnerBase[TModelInputForGPU]):
int(self.cache_config.cpu_offload_gb * 1024**3)) int(self.cache_config.cpu_offload_gb * 1024**3))
def load_model(self) -> None: def load_model(self) -> None:
logger.info("Starting to load model %s...", self.model_config.model)
with CudaMemoryProfiler() as m: with CudaMemoryProfiler() as m:
self.model = get_model(model_config=self.model_config, self.model = get_model(model_config=self.model_config,
device_config=self.device_config, device_config=self.device_config,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment