areusch commented on a change in pull request #8072:
URL: https://github.com/apache/tvm/pull/8072#discussion_r648453825
##
File path: python/tvm/micro/model_library_format.py
##
@@ -203,60 +209,200 @@ def _build_function_memory_map(function_metadata):
return ret
-def
areusch commented on a change in pull request #8072:
URL: https://github.com/apache/tvm/pull/8072#discussion_r648454905
##
File path: python/tvm/micro/model_library_format.py
##
@@ -203,60 +209,200 @@ def _build_function_memory_map(function_metadata):
return ret
-def
areusch commented on pull request #8213:
URL: https://github.com/apache/tvm/pull/8213#issuecomment-857824746
@kparzysz-quic yeah i think you're right--we get LLVM from APT in the docker
container, which i doubt has `-DLLVM_ENABLE_ASSERTIONS` as the website mentions
it's slow. For that
zackcquic commented on a change in pull request #8215:
URL: https://github.com/apache/tvm/pull/8215#discussion_r648448446
##
File path: tests/python/unittest/test_tvmscript_roundtrip.py
##
@@ -2888,6 +2888,67 @@ def test_opaque_block():
assert
hogepodge commented on pull request #8221:
URL: https://github.com/apache/tvm/pull/8221#issuecomment-857774248
Thank you!
--
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.
KJlaccHoeUM9l opened a new pull request #8224:
URL: https://github.com/apache/tvm/pull/8224
Add support of cpp RPC-server for Apple platform.
--
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
fantasyRqg commented on pull request #8223:
URL: https://github.com/apache/tvm/pull/8223#issuecomment-857752261
Android Application test log:
```
2021-06-09 22:21:48.114 12387-12428/com.rqg.tvm_rpc D/TVM_RUNTIME:
/Users/rqg/Playground/tvm/apps/cpp_rpc/rpc_server.cc:129: bind to
fantasyRqg opened a new pull request #8223:
URL: https://github.com/apache/tvm/pull/8223
Fix problem mentioned at #7390
Support `tvm_rpc` directly use in `adb shell` terminal
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 8a04efa Graph executor: remove unnecessary
tqchen merged pull request #8214:
URL: https://github.com/apache/tvm/pull/8214
--
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
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 5dc9627 [Metal] Remove matching Metal to OpenCL in
tqchen commented on pull request #8211:
URL: https://github.com/apache/tvm/pull/8211#issuecomment-857728596
Thanks @echuraev !
--
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
tqchen merged pull request #8211:
URL: https://github.com/apache/tvm/pull/8211
--
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
tqchen commented on pull request #8219:
URL: https://github.com/apache/tvm/pull/8219#issuecomment-857713812
Thanks @Beya2019 !
--
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
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 9899f1e Auto-tuning a Convolutional Network for ARM CPU (tutorial
error, bug reports) (#8103)
add 55459e7
tqchen merged pull request #8219:
URL: https://github.com/apache/tvm/pull/8219
--
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
leandron commented on a change in pull request #8212:
URL: https://github.com/apache/tvm/pull/8212#discussion_r648305205
##
File path: python/tvm/ir/transform.py
##
@@ -120,6 +120,11 @@ def current():
"""Return the current pass context."""
return
zhiics commented on a change in pull request #8212:
URL: https://github.com/apache/tvm/pull/8212#discussion_r648295913
##
File path: python/tvm/ir/transform.py
##
@@ -120,6 +120,11 @@ def current():
"""Return the current pass context."""
return
wyc-ruiker opened a new pull request #8222:
URL: https://github.com/apache/tvm/pull/8222
Pading conv2d NWHC/HWNC ops to legal shapes for using tensorcore on cuda
target and add some tests.
could you help review this pr? @jcf94 @Meteorix @jwfromm
--
This is an automated message from
mbaret commented on a change in pull request #7925:
URL: https://github.com/apache/tvm/pull/7925#discussion_r648188950
##
File path: src/te/operation/compute_op.cc
##
@@ -484,7 +484,9 @@ ComputeLoopNest ComputeLoopNest::Create(const
BaseComputeOpNode* self, const Sta
}
masahi commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857585536
Yeah CI runs PT deformable conv2d test with PT 1.7. It seems PT 1.8 changed
something in their deformable conv2d, the same test doesn't seem to work
anymore. Even after I apply the fix
jcf94 commented on pull request #8103:
URL: https://github.com/apache/tvm/pull/8103#issuecomment-857585349
Now merged. Thanks @cbswj @leandron @comaniac @tqchen
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
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 685ebda [VM] Better error messages (#8218)
add 9899f1e Auto-tuning a Convolutional Network for ARM CPU (tutorial
jcf94 merged pull request #8103:
URL: https://github.com/apache/tvm/pull/8103
--
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
zackcquic commented on a change in pull request #8220:
URL: https://github.com/apache/tvm/pull/8220#discussion_r648118036
##
File path: docs/api/python/ir.rst
##
@@ -23,6 +23,14 @@ tvm.ir
:autosummary:
+tvm.ir.instrument
Review comment:
Use tvm.instrument
merrymercy commented on pull request #7767:
URL: https://github.com/apache/tvm/pull/7767#issuecomment-857577881
#8221
--
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
ZihengJiang merged pull request #8218:
URL: https://github.com/apache/tvm/pull/8218
--
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,
codeislife99 edited a comment on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857572696
It is possible that relay and PT have different deform conv 2d results. I
had put up a PR https://github.com/apache/tvm/pull/7397 which fixed this for
PT 1.6 . It's
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/main by this push:
new 19501e7 add the overview image for the intro
codeislife99 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857572696
It is possible that relay and PT have different deform conv 2d results. I
had put up a PR which fixed this for PT 1.6 . It's possible they changed
something for later versions. My
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 5e006e0 [TIR] Fix data dependent indexing when lowering TE to TIR
(#8217)
add 685ebda [VM] Better error messages
ZihengJiang commented on pull request #8218:
URL: https://github.com/apache/tvm/pull/8218#issuecomment-857565969
Merged. Thanks @hypercubestart
--
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
mbaret commented on a change in pull request #7925:
URL: https://github.com/apache/tvm/pull/7925#discussion_r648128260
##
File path: python/tvm/tir/transform/inject_rolling_buffer.py
##
@@ -0,0 +1,238 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
merrymercy commented on pull request #8221:
URL: https://github.com/apache/tvm/pull/8221#issuecomment-857525699
cc @comaniac @hogepodge @junrushao1994
--
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
merrymercy opened a new pull request #8221:
URL: https://github.com/apache/tvm/pull/8221
- Improves the "Getting Started With TVM" series tutorials
- Fix some errors in the [introduction
FrozenGene commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648103811
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
+* Start Date: 2021-05-28
+* RFC
FrozenGene commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648064710
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
+* Start Date: 2021-05-28
+* RFC
tiandiao123 edited a comment on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857497838
If you guys can check, I found that the deformable conv2d ops of pytorch and
the deformable conv2d op of relay api have different result :
tiandiao123 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857497838
If you guys can check, I found that the deformable conv2d ops of pytorch and
the deformable conv2d op of relay api have different result :
tiandiao123 commented on issue #8057:
URL: https://github.com/apache/tvm/issues/8057#issuecomment-857496229
> thanks for that tip @masahi, I will start researching and trying to solve
the problem from there
Hi, does it have some progress? I have the same issue here.
--
This is
leandron commented on pull request #8212:
URL: https://github.com/apache/tvm/pull/8212#issuecomment-857480736
cc @mbaret can you also review and possibly merge?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
chiwwang opened a new pull request #8220:
URL: https://github.com/apache/tvm/pull/8220
Hi,
This is a follow-up PR on #7952
A How-To-Use-Pass-Instrument tutorial is added.
Pass Instrument sections are also added to pass_infra.rst.
@zackcquic @tqchen @areusch @tqchen
FrozenGene commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648058766
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
Review comment:
If so,
junrushao1994 commented on pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#issuecomment-857460287
CC: @jroesch @icemelon9 @kparzysz-quic @FrozenGene @jcf94
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648041157
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
Review comment:
junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648037427
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
+* Start Date: 2021-05-28
+*
junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648033968
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
+* Start Date: 2021-05-28
+*
junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r648032244
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,297 @@
+* Feature Name: Meta Schedule (AutoTensorIR)
+* Start Date: 2021-05-28
+*
Beya2019 opened a new pull request #8219:
URL: https://github.com/apache/tvm/pull/8219
Tvm script lacks tir.min node, we can use it like below
```
with tir.block([1024, 1024], "init") as [vi, vj]:
D[vi, vj] = tir.min(C[vi, vj], 0.0)
```
--
This is an
echuraev closed pull request #8210:
URL: https://github.com/apache/tvm/pull/8210
--
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
101 - 150 of 150 matches
Mail list logo