+1
TVM community progress is very good and its ready for graduation. Looking
forward to this.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#issuecomment-675870492
Yes, the problem I met is as @thierry mentioned, I want to have a specific
Vulkan runtime implementation for a specific device, but I didn't find a way to
pass the device information from the compiler to the runtime other than
modifying DLContext. Maybe there's a better way to do this?
--
+1, this is very exciting
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#issuecomment-675867143
+1 from me as well!
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#issuecomment-675857185
+1 TVM follows the Apache guideline well and has substantial impact in both
academia and industry. It sets a great example for a successful Apache project.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/a
Adding an example would be good. I believe that what @samyi is specifically
referring to are GPUs that have a shared memory with CPU for instance. For
instance if your vulkan GPU is integrated with the CPU, you can perform some
tricks, e.g. eliminate the staged copy when moving data from CPU t
+1 as well, I don't see any problems for TVM to graduate,
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#issuecomment-675818548
Thanks @samwyi it would be great to provide an example about what you mean by
device discovery. For example, we might be able to perform some formal setup to
select the device before start using one.
DLContext is specifically limited to the common terminology(in terms of device
id and device
While the TVM supports "device" specific compilation, the runtime side seems to
lack a mechanism to support device specific implementations. For example, one
vendor can have multiple devices for Vulkan target. Those devices may have
different runtime implementations due to the hardware differe
The community also have done several successful releases.
All the discussions and decisions have been done in the open and Apache way.
I agree that the project is ready for graduation as TLP in ASF.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly
+1
TVM not only follows the Apache guideline with great practices, but also
delivers the greatest features for users continuously. Glad to see the rapid
development and accomplishment of TVM and the community! Hope to see it
graduate smoothly!
--
You are receiving this because you are subscri
+1
I'm really excited about the progress that the TVM community has made! The
project is definitely ready for graduation.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#i
+1
Looking forward to this!
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6299#issuecomment-675763639
+1
TVM has been implementing many of the best practices of the ASF since before it
entered incubation. The project is ready :)
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6
Dear Community:
The TVM project has been an Apache incubator project for nearly 1.5 years now.
In the past one and half year, the community grew healthily under the Apache
way:
- The community now has 16 PPMC members, 31 committers, from a diverse list of
organizations.
- ~ 150 PRs merged eac
**Apache TVM Community Meeting, third Thursday of every month starting
September 17**
The TVM Community meetings will resume on Thursday, September 17 at 9 AM PT.
The meeting will be held monthly on every third Thursday. The basic starting
point for the agenda is:
* Introductions
* Sub Proje
@tobegit3hub Hi, i checked the cmake file again, i think the problem is: the
TF_TVMDSOOP.cmake file use findpackages() to find {python3_executable}, the
path it found's /usr/local/bin/python, but actually i am using a anaconda3 env
and i installed tensorflow in this env. i tried to set python3_
17 matches
Mail list logo
