A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 00:30 UTC
[Minor] Fix the path typo in loader.py: save_sharded_states.py -> save_sharded_state.py (#5151)
Signed-off-by: Ye Cao <caoye.cao@alibaba-inc.com>
Ye Cao committed
Jun 2, 2024 at 01:11 UTC
c35407282878cb3a42860d584a4d9eb6aed82299
1 file changed
+1
-1
vllm/model_executor/model_loader/loader.py
+1
-1
@@ -386,7 +386,7 @@ class ShardedStateLoader(BaseModelLoader):
386
Model loader that directly loads each worker's model state dict, which
387
enables a fast load path for large tensor-parallel models where each worker
388
only needs to read its own shard rather than the entire checkpoint. See
389
- `examples/save_sharded_states.py` for creating a sharded checkpoint.
389
+ `examples/save_sharded_state.py` for creating a sharded checkpoint.
390
"""
391
392
DEFAULT_PATTERN = "model-rank-{rank}-part-{part}.safetensors"