Usually, `USE_VULKAN=ON` should be enough to enable spirv codegen and vulkan
runtime.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-set-cmake-config-to-let-tvm-support-spirv/12971/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe fro
Can anyone explain to me the comments for spirv config?
https://github.com/apache/tvm/blob/ada4c46f095f876efd97c4d0a3bf8860d7c5d5e8/cmake/config.cmake#L84-L90
How can I modify this config to let TVM supports spirv?
By the way, does TVM have code reviews? Why is there such an obvious error in
the
The new blocks are intentionally ignored
---
[Visit
Topic](https://discuss.tvm.apache.org/t/metaschedule-postorderapply-cannot-deal-with-newly-added-blocks/12968/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](h
Good to know, will do, thanks.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/byoc-how-backwards-compatible-does-the-tensorrt-partition-for-tensorrt-function-need-to-be/12957/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails
Hi, all. I find that the PostOrderApply space generator cannot deal with blocks
added by previous schedule rules in the implementation
[here](https://github.com/apache/tvm/blob/24010db6c0e90bc555f6d12e23381fa7b00cf25d/src/meta_schedule/space_generator/post_order_apply.cc#L110-L122),
which mea
Excuse me. Sorry to bother you.
When I use **efficientnetv2-b0** to do real time classification on 1080ti
The model layout is NCHW and I use 2 trials,FPS is about 33.
And I try to convert my model layout to NHWC,the tuning parameters are same as
the previous work,FPS is about 30.
In **effic
Thanks @comaniac.
The compilation phase changes looks good. Could you maintain the runtime
environment variable compatibility otherwise it will impact our existing users.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/byoc-how-backwards-compatible-does-the-tensorrt-partition-for-tens
