[Neuron] Support inference with transformers-neuronx (#2569)

2024-02-28 09:34:34 -08:00
parent e46fa5d52e
commit 3b7178cfa4
18 changed files with 516 additions and 42 deletions
--- a/vllm/model_executor/init.py
+++ b/vllm/model_executor/init.py
@@ -1,7 +1,6 @@
 from vllm.model_executor.input_metadata import InputMetadata
-from vllm.model_executor.model_loader import get_model
 from vllm.model_executor.sampling_metadata import SamplingMetadata
-from vllm.model_executor.utils import set_random_seed
+from vllm.model_executor.utils import set_random_seed, get_model

 __all__ = [
    "InputMetadata",