Currently, we deploy all benchmark inputs once. While it makes perfect sense for some data (like ML model), for other inputs, it might make sense to duplicate other inputs. For example, if we plan 100 concurrent invocations, we can replicate the input image 100 times.
Similarly, we should cache and replicate inputs in NoSQL storage. Right now, we generate new input with different unique ID for every invocation. This needs to be cached and replicated, reusing across invocations.
Currently, we deploy all benchmark inputs once. While it makes perfect sense for some data (like ML model), for other inputs, it might make sense to duplicate other inputs. For example, if we plan 100 concurrent invocations, we can replicate the input image 100 times.
Similarly, we should cache and replicate inputs in NoSQL storage. Right now, we generate new input with different unique ID for every invocation. This needs to be cached and replicated, reusing across invocations.