Update or followup about AWS Neuron for possible support for new AWS inferential chip?

[Henry Saputra <he...@gmail.com>]

Hi All,

I remember someone asked about AWS Neuron SDK [1] during TVM summit.
AFAIK it is used to support AWS new Inferentia chip that focus for low
power and low precision inferences jobs.

Does anyone have followup whether would make sense to add support in TVM
for the new AWS Inferentia chip [2]?

Thanks,

Henry


[1] https://github.com/aws/aws-neuron-sdk
[2] https://aws.amazon.com/machine-learning/inferentia/

Re: Update or followup about AWS Neuron for possible support for new AWS inferential chip?

[YiZhi Liu <ea...@gmail.com>]

Hi Henry,

Thanks for asking the question. It depends on how and to what extent
AWS is gonna release its low level API. To put on my Amazon hat (and I
work closely with inferentia team), this is still not clear. We need
more time to investigate.

It is definitely feasible If we only treat TVM as a model converter
for neuron-sdk. Though it also requires neuron-sdk to clean and expose
some high level APIs.

On Wed, Jan 15, 2020 at 11:59 AM Henry Saputra <he...@gmail.com> wrote:
>
> Hi All,
>
> I remember someone asked about AWS Neuron SDK [1] during TVM summit.
> AFAIK it is used to support AWS new Inferentia chip that focus for low
> power and low precision inferences jobs.
>
> Does anyone have followup whether would make sense to add support in TVM
> for the new AWS Inferentia chip [2]?
>
> Thanks,
>
> Henry
>
>
> [1] https://github.com/aws/aws-neuron-sdk
> [2] https://aws.amazon.com/machine-learning/inferentia/



-- 
Yizhi Liu

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@tvm.apache.org
For additional commands, e-mail: dev-help@tvm.apache.org