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, 05:30 UTC
[Minor] Fix a small typo (#2672)
Philipp Moritz committed
Jan 30, 2024 at 13:40 UTC
bbe9bd9684218038cca9663ac79dfe7c4f28a351
1 file changed
+1
-1
vllm/model_executor/parallel_utils/parallel_state.py
+1
-1
@@ -117,7 +117,7 @@ def model_parallel_is_initialized():
117
def get_tensor_model_parallel_group():
118
"""Get the tensor model parallel group the caller rank belongs to."""
119
assert _TENSOR_MODEL_PARALLEL_GROUP is not None, (
120
- "tenosr model parallel group is not initialized")
120
+ "tensor model parallel group is not initialized")
121
return _TENSOR_MODEL_PARALLEL_GROUP
122
123