Posts tagged announce-end-of-support

Announcing end-of-support for implicit asynchronous mode in Neuron Runtime

A future release of the Neuron SDK will remove support for implicit asynchronous mode, including the NEURON_RT_ASYNC_EXEC_MAX_INFLIGHT_REQUESTS environment variable.

Customers using the implicit request async APIs must migrate their code and calls to the new Neuron Runtime async APIs. For details on the new APIs, see Neuron Runtime Async APIs: Motivation and Overview.

Read more ...


Announcing end-of-support for --model-type=transformer-inference compiler flag

Starting with Neuron release 2.14, the --model-type=transformer-inference compiler flag is deprecated.

Neuron SDK users using the --model-type=transformer-inference compiler flag are highly encouraged to migrate to the --model-type=transformer compiler flag.

Read more ...