zhanghaohit commented on pull request #6126:
URL: https://github.com/apache/tvm/pull/6126#issuecomment-822200672
> [apache/tvm-vta#24](https://github.com/apache/tvm-vta/pull/24) is now
merged, we should be good to update the submodule and CI
@tmoreau89 Great. I've update the submodul
FrozenGene commented on a change in pull request #7877:
URL: https://github.com/apache/tvm/pull/7877#discussion_r615512179
##
File path: include/tvm/auto_scheduler/measure.h
##
@@ -340,9 +351,14 @@ class LocalBuilderNode : public ProgramBuilderNode {
public:
/*! \brief Bui
eleflea commented on issue #7872:
URL: https://github.com/apache/tvm/issues/7872#issuecomment-822129214
@masahi After researching, I think it is a problem of quantized grouped
convolution, and it cannot be quantified in multiple groups. Please refer to
#7878 for the specific reproducible s
eleflea opened a new issue #7878:
URL: https://github.com/apache/tvm/issues/7878
Hi
I find a bug of relay. I used pytorch to quantize a grouped convolution
model, and an error was reported in `relay.frontend.from_pytorch` function.
Detailed as follows.
```
import tvm
from tvm i
jcf94 commented on a change in pull request #7877:
URL: https://github.com/apache/tvm/pull/7877#discussion_r615504135
##
File path: include/tvm/auto_scheduler/measure.h
##
@@ -340,9 +351,14 @@ class LocalBuilderNode : public ProgramBuilderNode {
public:
/*! \brief Build fu
apeskov opened a new pull request #7877:
URL: https://github.com/apache/tvm/pull/7877
Introduce callback based async API for Builder/Runner. It allows to build
async pipelines for kernel evaluation. Totally it speeds up measure process by
overlapping build and run stages.
--
This is an
apeskov opened a new pull request #7876:
URL: https://github.com/apache/tvm/pull/7876
This patch introduces tracker support for iOS roc application. That is
mandatory functionality for auto tuning process for iOS platform.
This is a port of app/cpp_rpc sources.
Also Fontaine'
apeskov opened a new pull request #7875:
URL: https://github.com/apache/tvm/pull/7875
This PR is a part of iOS enabling efforts. Particularly it allows to use
regular TVM RPC mechanics in the way like for Android platform.
Essential part of auto tuning on real iOS device is an abilit
junrushao1994 commented on a change in pull request #7873:
URL: https://github.com/apache/tvm/pull/7873#discussion_r615443552
##
File path: src/tir/transforms/plan_update_buffer_allocation_location.cc
##
@@ -0,0 +1,169 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF)
junrushao1994 commented on pull request #7873:
URL: https://github.com/apache/tvm/pull/7873#issuecomment-822047228
Shall we find a shorter name this this pass 😆
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
K1504296 commented on issue #7470:
URL: https://github.com/apache/tvm/issues/7470#issuecomment-822027652
Hello,
Any updates on this? I'm consistently running into a similar error in
verify_crop_and_resize() on aarch64 devices when running
task_python_integration.py.
```
tests/
K1504296 commented on issue #7799:
URL: https://github.com/apache/tvm/issues/7799#issuecomment-822023089
It seems to be a problem related to LLVM. LLVM 6.0 returns a Segmentation
Fault; however, LLVM 10.0 gets stuck during execution. Running with gdb and
LLVM 10.0 the following is returned
tmoreau89 commented on pull request #7874:
URL: https://github.com/apache/tvm/pull/7874#issuecomment-822019751
@tqchen thanks for the submodule bump; I was thinking that it gets done as
part of https://github.com/apache/tvm/pull/6126 in order to be consistent with
the rest of the hw tests.
tmoreau89 commented on pull request #6126:
URL: https://github.com/apache/tvm/pull/6126#issuecomment-822019563
https://github.com/apache/tvm-vta/pull/24 is now merged, we should be good
to update the submodule and CI
--
This is an automated message from the Apache Git Service.
To respond
tqchen opened a new pull request #7874:
URL: https://github.com/apache/tvm/pull/7874
cc @tmoreau89 , should fix the verilator problem in the mainline ci
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
This is an automated email from the ASF dual-hosted git repository.
jcf94 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 9a72ba3 [frontend][tflite] float16 quant support (#7736)
add 1fb32b0 [TIR] An analysis pass to calculate workspace s
jcf94 merged pull request #7859:
URL: https://github.com/apache/tvm/pull/7859
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please conta
Hzfengsy opened a new pull request #7873:
URL: https://github.com/apache/tvm/pull/7873
This PR is part of the TensorIR upstreaming effort (#7527) as one of the M1c
stages, introducing the pass PlanUpdateBufferAllocationLocation.
This Pass will Locate the buffer allocation to the exac
masahi commented on issue #7872:
URL: https://github.com/apache/tvm/issues/7872#issuecomment-821960212
Can you give us a complete reproducible script?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to g
manupa-arm commented on pull request #7859:
URL: https://github.com/apache/tvm/pull/7859#issuecomment-821958968
@jcf94 Yes, we are planning to use it there and we think it'd be a good
utility for memory planning project as well.
--
This is an automated message from the Apache Git Service
w-tingting opened a new issue #7872:
URL: https://github.com/apache/tvm/issues/7872
Hi! I quantified a model with Pytorch, and I am stuck with a problem in the
process of transforming this model with TVM.The code is as follows:
```
inp = torch.rand(1, 3, 32, 32)
model =
21 matches
Mail list logo
