xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 05:55:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] fix typo and add detailed log (#28178)

Browse Source 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
This commit is contained in:
Ning Xie 2025-11-09 13:33:46 +08:00 committed by GitHub
parent 3a7d580343
commit e5e9067e61
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/offline_inference/load_sharded_state.py
View File

@ -11,7 +11,7 @@ python save_sharded_state.py \
--model /path/to/load \ --model /path/to/load \
--quantization deepspeedfp \ --quantization deepspeedfp \
--tensor-parallel-size 8 \ --tensor-parallel-size 8 \
--output /path/to/save/sharded/modele --output /path/to/save/sharded/model
python load_sharded_state.py \ python load_sharded_state.py \
--model /path/to/saved/sharded/model \ --model /path/to/saved/sharded/model \

2
vllm/v1/worker/gpu_model_runner.py
View File

@ -3035,7 +3035,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
time_after_load = time.perf_counter() time_after_load = time.perf_counter()
self.model_memory_usage = m.consumed_memory self.model_memory_usage = m.consumed_memory
logger.info_once( logger.info_once(
"Model loading took %.4f GiB and %.6f seconds", "Model loading took %.4f GiB memory and %.6f seconds",
self.model_memory_usage / GiB_bytes, self.model_memory_usage / GiB_bytes,
time_after_load - time_before_load, time_after_load - time_before_load,
scope="local", scope="local",