Tianqi Chen
Tianqi Chen
@chunit-quic just want to check in and see where we are on this
i think some changes that @MasterJH5574 introduced recently would alleviate this situation if we bring outputs that have a maximum upper bound
This is an exciting milestone for the community and helps us to collectively evolve the project to empower genAI, looking forward to working with everyone to bring more exciting changes...
Forum post for followup discussions https://discuss.tvm.apache.org/t/main-now-transitions-to-unity/16277/2
@cbalint13 do you mind to rebase on latest main? love to get it in
Thanks @srkreddy1238 . Reading the set of changes, i feel that we need something that is more lifted out from the DeviceAPI since this is getting closer to the two...
One thing that I can probably do is do do a bit of refactoring and bring it to runtime folder so we can leverage it in most places, I may...
I think it is fine dropping them, but let us also keep the backward compatibility in mind. It might be useful to first introduce json exchange format, and then allow...
It is possible for the tensor continue to be shared, the mechanism is that making DLTensor export incref the tensor, and have DLManagedTensor's deleter decref the reference counter, rather than...
Thank you, can you provide some high-level description about the device, the state of the driver, and the possible intention of the use of the API. Thank you