Closed kandakji closed 3 weeks ago
Hi,
This PR updates the inference documentation for hugging face on sagemaker. This adds a note about Pipelines lack of multi-threading support, which can represent a CPU bottleneck in sagemaker inference endpoints.
Hi,
This PR updates the inference documentation for hugging face on sagemaker. This adds a note about Pipelines lack of multi-threading support, which can represent a CPU bottleneck in sagemaker inference endpoints.