yes, in the case of DSO module the engine creation is a function emitted by the
codegen.
Note that my main point is about de-coupling(the meta-data(weights) from
weight) and it would be good to discuss further what the class should look
like. In terms of the code part, we could certainly allo
This is a draft PR and only for discussion but not for merging as is.
These are a couple of commits that show a proof of concept about how we could
restructure and improve the tflite frontend. I've lightly tested these by
compiling a couple of tflite models to give me some confidence that they w
Edit: posting this reply separately for link snapshotting purposes:
@ramana-arm Great points and we will make sure that any discussion in an online
meetup is a complement, rather than a substitute for RFCs, Github issues, and
discuss threads.
---
[Visit Topic](https://discuss.tvm.ai/t/tv
Thanks for the quesitions
The JSON proposal is another layer of abstraction that serves as a interpreter
for general workloads. As it defers the running of the library code by
interpreting the "bytecode" in this case defined by a json format. I understand
the objective this RFC proposes, as n
Thanks for the explanation. I have a further question based on your example.
If I understand correctly, this example works for a scenario that a customized
codegen will generate metadata and kernel code. The kernel code here may
include external library APIs or graph execution engine that inte
Here is an example(I also updated my code above according as there is a minor
problem), to construct the code manually
```python
mod = ModuleMetaDataWrapper(metadata)
mod.import_module(CSourceModule(dnnl_code);
mod.export_library("xyz.so")
loaded = tvm.runtime.load_module("xyz.so");
```
Afte
@ramana-arm Great points and we will make sure that any discussion in an online
meetup is a complement, rather than a substitute for RFCs, Github issues, and
discuss threads.
## First OctoML Apache TVM Online Meetup - May 21
Okay, I'd like to go ahead and give this a try. Thursday, May 21 at 9
@tqchen Thanks for the comment and sharing of thoughts. Yes, the fundamental
problem here is the serialization of code and weights. Code is relatively easy
to handle and weights are the real problem. I agree that a json runtime
introduces another layer of abstraction for graph which the curren
Any more opinions ?
Ramana
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-improve-pull-requests-with-respect-to-bug-fixes/6529/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsub
[quote="tqchen, post:4, topic:6579"]
this->imported_modules[0]->GetFunction("__DestroyModule"); destroy(); }
GetFunction(name) { if (name != "__InitModule" && name != "__DestroyModule") {
return this->imported_modules[0]->GetFunction(name); }
[/quote]
also cc @FrozenGene @junrushao1994
--
I think these are fair problems, and json is an OK solution for some particular
backends. However, I think it is in particular important for us to think about
the infrastructure implication in the long run. I think we want to discuss the
solution in a case by case manner.
The JSON runtime is
Thanks, I think this will be very useful. I think the benefit of this approach
is that it allows the run-time to be customized much more easily. I like the
idea of being able to cache an *engine* (in my case this will be a series of
ACL functions) - this opens up opportunity for optimization o
This would be a welcome addition to the BYOC infrastructure, particularly in
reducing the fragmentation between approaches for different backends. I think
it's also important we have a robust alternative to the CSourceModule approach
as it's becoming clear that's not yet suitable for full scal
You are right. Thank you for figuring out the bug.
That's would be my fault that I focused on the classical workload (e.g.
resnet), but forgot to test large shapes. It's easy to fix. Can you please
create a PR?
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-tensor-core-optimization-of-cn
Hi,
I have tried to tune my conv2d workload ['NHWC', (32, 300, 300, 64)], but it
failed for cuLaunchKernel's Grid_dim(2, 4, 9(>65535)).
```
bz = s[output].fuse(hi, wi)
s[output].bind(bz, block_z)
```
It seems like there should be a H/W direction tiling config to support all
shapes.
-
15 matches
Mail list logo
