[TVM Discuss] [RFC] [RFC] New GraphRuntime API to share parameter between modules

@yinghai I think it needs to be done in `SetupStorage` (using a dummy `NDArray` instance instead of `NDArray::Empty`). If I understood correctly, we don't need to mix `SetInput` and `SeInputZeroCopy`, just add `SetSharedInput` to take a `NDArray` input should be fine. --- [Visit Topic](h

Re: [dmlc/tvm] [RFC] [Contrib] [Runtime] Minimal runtime (~12kb .text on ARMv7/x86) for subset of TVM models (#3567)

Given the current discussions, perhaps we can decide on the naming, do a few improvement if you feel you can push some of them in a few days. Then we merge it in. In terms of naming and code location, given the relation to uTVM. We could think about a good name for the minimal runtime. One exa

Re: [dmlc/tvm] [RFC][Quantization] Support quantized models from TensorflowLite (#2351)

I agree, we should move the proposal to a new thread. Yes, I can lead the proposal discussion. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2351#issuecomment-513025651

Re: [dmlc/tvm] [DEV] TVM v0.6 Roadmap (#2623)

There has been quite a lot of improvements recently. While it is up to the community, I think we might be able to get out something around Sep -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issue

Re: [dmlc/tvm] [RFC][Quantization] Support quantized models from TensorflowLite (#2351)

@anijain2305 can you lead the proposal discussion? -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2351#issuecomment-513014013

Re: [dmlc/tvm] [RFC][Quantization] Support quantized models from TensorflowLite (#2351)

The discussion in this thread has get quite long and given that we are converging. I recommend we close this thread, and open a new RFC thread "QNN Dialect". With latest proposals of the APIs that @anijain2305 @shoubhik is putting together. This way we keep the community informed and we can mo

Re: [dmlc/tvm] [RFC] [Contrib] [Runtime] Minimal runtime (~12kb .text on ARMv7/x86) for subset of TVM models (#3567)

>From what I see and also summarize the discussion: - No new/delete, but allows use of custom allocators that does arena-like allocations. - C++ is fine, template is fine, but maybe no stl The arena-style allocator may be fine for most of our cases, the idea is that we always allocate and de-al

Re: [dmlc/tvm] [RFC] [Contrib] [Runtime] Minimal runtime (~12kb .text on ARMv7/x86) for subset of TVM models (#3567)

@ajtulloch the situation is not black and white, at one end of the scale is pure 'C' at the other end of the scale is 'C++' using the standard c++ libraries and all the language bells and whistles, in the middle is a bunch of intermediate restricted subsets of c++ with arbitrary subsets of the

[TVM Discuss] [Development] Request for invite to the slack channel

Thanks! I've now joined. --- [Visit Topic](https://discuss.tvm.ai/t/request-for-invite-to-the-slack-channel/2888/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/b98aa0036

[TVM Discuss] [Development] Request for invite to the slack channel

[quote="jdavies-huawei, post:1, topic:2888"] [jessica.dav...@huawei.com](mailto:jessica.dav...@huawei.com). [/quote] sorry for the delayed action both invitation sent --- [Visit Topic](https://discuss.tvm.ai/t/request-for-invite-to-the-slack-channel/2888/4) to respond. You are receiving

[TVM Discuss] [Development] Request for invite to the slack channel

Hi Shang, unfortunately no one has replied to my request yet, so I haven't been able to join the slack channel. --- [Visit Topic](https://discuss.tvm.ai/t/request-for-invite-to-the-slack-channel/2888/3) to respond. You are receiving this because you enabled mailing list mode. To unsubsc

[TVM Discuss] [Development] Request for invite to the slack channel

Hi Jessica, I'm wondering if you already joined the slack channel? If so, could you send an invite to me as well? wangs...@cs.toronto.edu. Thanks! Shang --- [Visit Topic](https://discuss.tvm.ai/t/request-for-invite-to-the-slack-channel/2888/2) to respond. You are receiving this because

Re: [dmlc/tvm] [RFC] [Contrib] [Runtime] Minimal runtime (~12kb .text on ARMv7/x86) for subset of TVM models (#3567)

> This looks great. As mentioned above it potentially fits well with uTVM. For > use with uTVM it would be useful to have this runtime or a derivative built > in C rather than C++ in order to be deployable to the various embedded > environments out there that don't have C++ runtime / tooling sup

Re: [dmlc/tvm] [Community] Zhi Chen -> Committer (#3572)

Merged #3572 into master. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/pull/3572#event-2493428567

Re: [dmlc/tvm] [RFC] [Contrib] [Runtime] Minimal runtime (~12kb .text on ARMv7/x86) for subset of TVM models (#3567)

This looks great. As mentioned above it potentially fits well with uTVM. For use with uTVM it would be useful to have this runtime or a derivative built in C rather than C++ in order to be deployable to the various embedded environments out there that don't have C++ runtime / tooling support.