You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A NVIDIA GPU powered machine with CUDA Toolkit installed is required to build a Faiss base Image and to run the Docker images to build an index.
109
+
A NVIDIA GPU powered machine with CUDA Toolkit installed is required to build a Faiss base image and to run the Docker images to build an index.
110
110
111
-
Typically an [EC2 G5](https://aws.amazon.com/ec2/instance-types/g5/) 2xlarge instance running a Deep Learning OSS Nvidia Driver AMI, with Docker CLI installed is recommended for development use.
111
+
Typically an [EC2 G5](https://aws.amazon.com/ec2/instance-types/g5/) 2xlarge instance running a Deep Learning OSS Nvidia Driver AMI with Docker CLI installed is recommended for development use.
112
112
113
113
[Setup an EC2 Instance](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/EC2_GetStarted.html)
114
114
@@ -118,7 +118,7 @@ Simple memory profiling can be done during development to get memory usage stati
118
118
119
119
### GPU Memory Profiling with NVIDIA SMI
120
120
121
-
1. Install [py3nvml](https://pypi.org/project/py3nvml/): In [`/remote_vector_index_builder/core/requirements.txt`](/remote_vector_index_builder/core/requirements.txt) add py3nvml on a newline.
121
+
1. Install [py3nvml](https://pypi.org/project/py3nvml/): In [`/remote_vector_index_builder/core/requirements.txt`](/remote_vector_index_builder/core/requirements.txt) add `py3nvml` on a newline.
122
122
123
123
2. Add import statement and initialize method in the file containing the driver code.
0 commit comments