siju-samuel commented on pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#issuecomment-646437081
@t-vi please rebase.
This is an automated message from the Apache Git Service.
To respond to the
tmoreau89 commented on pull request #5842:
URL: https://github.com/apache/incubator-tvm/pull/5842#issuecomment-646427274
CC-ing @vegaluisjose @huajsj @pasqoc
This is an automated message from the Apache Git Service.
To
tmoreau89 commented on pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-646427173
CC-ing @vegaluisjose @huajsj @pasqoc
This is an automated message from the Apache Git Service.
To
tmoreau89 commented on pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-646427144
CC-ing @vegaluisjose @huajsj @pasqoc
This is an automated message from the Apache Git Service.
To
FrozenGene commented on a change in pull request #5754:
URL: https://github.com/apache/incubator-tvm/pull/5754#discussion_r442604112
##
File path: src/relay/op/nn/convolution.h
##
@@ -383,6 +383,38 @@ inline bool Conv2DWinogradWeightTransformRel(const
Array& types, int num_i
liangfu commented on a change in pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#discussion_r442601905
##
File path: config/intelfocl_sample.json
##
@@ -0,0 +1,13 @@
+{
+ "TARGET" : "intelfocl",
Review comment:
I think this should be the
masahi opened a new pull request #5850:
URL: https://github.com/apache/incubator-tvm/pull/5850
https://github.com/apache/incubator-tvm/pull/4458
@yzhliu
This is an automated message from the Apache Git Service.
To
tqchen merged pull request #5849:
URL: https://github.com/apache/incubator-tvm/pull/5849
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.
tqchen pushed a commit to branch v0.6
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/v0.6 by this push:
new 09cedf6 [BACKPORT-0.6][BUGFIX] Fixed
junrushao1994 commented on pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#issuecomment-646395649
@zhiics Could you take another look? Thanks!
This is an automated message from the Apache Git
kazum commented on pull request #5830:
URL: https://github.com/apache/incubator-tvm/pull/5830#issuecomment-646390576
@jroesch Can we enable derive_default for bindgen? Otherwise, test_wasm32
fails with tvm-sys because of the generated padding field.
The following change looks
leonwanghui commented on a change in pull request #5830:
URL: https://github.com/apache/incubator-tvm/pull/5830#discussion_r442579653
##
File path: rust/tvm-graph-rt/src/array.rs
##
@@ -0,0 +1,400 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or
yzhliu opened a new pull request #5849:
URL: https://github.com/apache/incubator-tvm/pull/5849
#4844
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
xqdan commented on a change in pull request #5772:
URL: https://github.com/apache/incubator-tvm/pull/5772#discussion_r442577797
##
File path: src/arith/rewrite_simplify.cc
##
@@ -353,6 +353,25 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
SubNode* op) {
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442577192
##
File path: include/tvm/node/container.h
##
@@ -43,51 +44,1200 @@ using runtime::Downcast;
using runtime::IterAdapter;
using
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442576289
##
File path: tests/cpp/container_test.cc
##
@@ -324,6 +324,29 @@ TEST(Map, Iterator) {
CHECK(map2[a].as()->value == 2);
}
+TEST(Map,
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442576113
##
File path: tests/cpp/container_test.cc
##
@@ -310,7 +310,7 @@ TEST(Map, Mutate) {
CHECK(it != dict.end() && (*it).second.same_as(x));
xqdan commented on a change in pull request #5772:
URL: https://github.com/apache/incubator-tvm/pull/5772#discussion_r442573174
##
File path: src/arith/rewrite_simplify.cc
##
@@ -353,6 +353,25 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
SubNode* op) {
xqdan commented on a change in pull request #5772:
URL: https://github.com/apache/incubator-tvm/pull/5772#discussion_r442573174
##
File path: src/arith/rewrite_simplify.cc
##
@@ -353,6 +353,25 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
SubNode* op) {
anijain2305 commented on pull request #5805:
URL: https://github.com/apache/incubator-tvm/pull/5805#issuecomment-646373994
@vinx13 Can you PTAL?
This is an automated message from the Apache Git Service.
To respond to the
zhiics commented on a change in pull request #5772:
URL: https://github.com/apache/incubator-tvm/pull/5772#discussion_r442565117
##
File path: src/arith/rewrite_simplify.cc
##
@@ -353,6 +353,25 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
SubNode* op) {
junrushao1994 commented on a change in pull request #5601:
URL: https://github.com/apache/incubator-tvm/pull/5601#discussion_r442561558
##
File path: include/tvm/runtime/data_type.h
##
@@ -72,6 +73,9 @@ class DataType {
data_.code = static_cast(code);
data_.bits =
zhiics commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442559193
##
File path: tests/cpp/container_test.cc
##
@@ -324,6 +324,29 @@ TEST(Map, Iterator) {
CHECK(map2[a].as()->value == 2);
}
+TEST(Map, Insert)
junrushao1994 commented on a change in pull request #5838:
URL: https://github.com/apache/incubator-tvm/pull/5838#discussion_r442558981
##
File path: include/tvm/target/target_id.h
##
@@ -0,0 +1,228 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or
tqchen commented on a change in pull request #5838:
URL: https://github.com/apache/incubator-tvm/pull/5838#discussion_r442558792
##
File path: include/tvm/target/target_id.h
##
@@ -0,0 +1,228 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tqchen commented on pull request #5601:
URL: https://github.com/apache/incubator-tvm/pull/5601#issuecomment-646355311
@junrushao1994 @ZhennanQin please followup and
https://tvm.apache.org/docs/contribute/code_review.html#approve-and-request-changes-explicitly
tqchen merged pull request #5821:
URL: https://github.com/apache/incubator-tvm/pull/5821
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.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 24df0ba Additional canonicalization added for AddNode (#5846)
add 64766c2 [AutoTVM] Suppress the
tqchen commented on pull request #5795:
URL: https://github.com/apache/incubator-tvm/pull/5795#issuecomment-646354939
@icemelon9 please manage this PR
This is an automated message from the Apache Git Service.
To respond to
tqchen commented on pull request #5805:
URL: https://github.com/apache/incubator-tvm/pull/5805#issuecomment-646354778
@anijain2305 please help to manage this PR
This is an automated message from the Apache Git Service.
To
tqchen commented on pull request #5772:
URL: https://github.com/apache/incubator-tvm/pull/5772#issuecomment-646354577
cc @zhiics @yongfeng-nv @merrymercy @jroesch please help to take a look
This is an automated message from
tqchen commented on pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#issuecomment-646353977
@zhiics please take another look and
https://tvm.apache.org/docs/contribute/code_review.html#approve-and-request-changes-explicitly
cc @wweic @spectrometerHBH
junrushao1994 commented on a change in pull request #5838:
URL: https://github.com/apache/incubator-tvm/pull/5838#discussion_r442552581
##
File path: include/tvm/target/target_id.h
##
@@ -0,0 +1,228 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or
anijain2305 opened a new pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848
This is by no way ready (lots of hack and duplication currently). This is to
kick start the discussion for TFLite2.x quantization model ingestion
Checked on MNIST model -
tqchen commented on a change in pull request #5838:
URL: https://github.com/apache/incubator-tvm/pull/5838#discussion_r442552150
##
File path: include/tvm/target/target_id.h
##
@@ -0,0 +1,228 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tqchen commented on a change in pull request #5838:
URL: https://github.com/apache/incubator-tvm/pull/5838#discussion_r442552006
##
File path: include/tvm/target/target_id.h
##
@@ -0,0 +1,228 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tqchen merged pull request #5846:
URL: https://github.com/apache/incubator-tvm/pull/5846
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.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from d85efa1 fix batchnorm infer_value error, add regression test and unit
test (#5845)
add 24df0ba
tqchen commented on pull request #5846:
URL: https://github.com/apache/incubator-tvm/pull/5846#issuecomment-646352898
thanks @ANSHUMAN87
This is an automated message from the Apache Git Service.
To respond to the message,
comaniac opened a new pull request #5847:
URL: https://github.com/apache/incubator-tvm/pull/5847
#5760 introduces new patterns (dtype and shape). This PR updates the
document to reflect those updates.
cc @mbrookhart
mbrookhart commented on pull request #5826:
URL: https://github.com/apache/incubator-tvm/pull/5826#issuecomment-646347835
Hitting an issue with dynamic shapes on GPU with the VM.
This is an automated message from the Apache
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from d8c80c3 `tvm` crate stage 3 of Rust refactor (#5769)
add eacfe89 [RUNTIME] Introduce MetadataModule
tqchen merged pull request #5845:
URL: https://github.com/apache/incubator-tvm/pull/5845
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.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from eacfe89 [RUNTIME] Introduce MetadataModule to separate code
compilation/interpretation and weight
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r442534625
##
File path: python/tvm/runtime/module.py
##
@@ -41,6 +41,10 @@ def __init__(self, handle):
self.handle = handle
self._entry
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r442534625
##
File path: python/tvm/runtime/module.py
##
@@ -41,6 +41,10 @@ def __init__(self, handle):
self.handle = handle
self._entry
FrozenGene commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r442534625
##
File path: python/tvm/runtime/module.py
##
@@ -41,6 +41,10 @@ def __init__(self, handle):
self.handle = handle
self._entry
tqchen merged pull request #5770:
URL: https://github.com/apache/incubator-tvm/pull/5770
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
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442509398
##
File path: include/tvm/node/container.h
##
@@ -43,51 +44,1188 @@ using runtime::Downcast;
using runtime::IterAdapter;
using
zhiics commented on a change in pull request #5770:
URL: https://github.com/apache/incubator-tvm/pull/5770#discussion_r442490987
##
File path: python/tvm/contrib/graph_runtime.py
##
@@ -162,7 +162,12 @@ def set_input(self, key=None, value=None, **params):
keys =
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442488594
##
File path: include/tvm/node/container.h
##
@@ -43,51 +44,1188 @@ using runtime::Downcast;
using runtime::IterAdapter;
using
tqchen commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r442478436
##
File path: include/tvm/node/container.h
##
@@ -43,51 +44,1188 @@ using runtime::Downcast;
using runtime::IterAdapter;
using
tqchen commented on a change in pull request #5770:
URL: https://github.com/apache/incubator-tvm/pull/5770#discussion_r442477655
##
File path: python/tvm/contrib/graph_runtime.py
##
@@ -162,7 +162,12 @@ def set_input(self, key=None, value=None, **params):
keys =
ANSHUMAN87 opened a new pull request #5846:
URL: https://github.com/apache/incubator-tvm/pull/5846
The PR has 2 issue fix:
1: 2 + x was always operated as x + 2. It hides certain match condition.
2: Canonicalize (c1 - y) + x --> (x - y) + c1
cc @yzhliu , @zhiics , @tqchen
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch egg
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
at d8c80c3 `tvm` crate stage 3 of Rust refactor (#5769)
No new revisions were added by this update.
jroesch commented on pull request #5830:
URL: https://github.com/apache/incubator-tvm/pull/5830#issuecomment-646242260
@robo-corg @tqchen this is like a straight copy of the old `runtime` crate
with slight modifications to use the new `tvm-sys`. After this patch lands I
can send a final
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/master by this push:
new d8c80c3 `tvm` crate stage 3 of Rust
jroesch merged pull request #5769:
URL: https://github.com/apache/incubator-tvm/pull/5769
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
junrushao1994 commented on pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#issuecomment-646226758
@tqchen Just responded to all the review comments, added test cases and code
comments, could you take another look?
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 082874c [Torch][Quantized] Fix converting serialized quantized models
(#5839)
add 9ba98be ffi
tqchen merged pull request #5843:
URL: https://github.com/apache/incubator-tvm/pull/5843
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
tqchen commented on pull request #5843:
URL: https://github.com/apache/incubator-tvm/pull/5843#issuecomment-646226767
Thanks @t-vi !
This is an automated message from the Apache Git Service.
To respond to the message, please
junrushao1994 edited a comment on pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#issuecomment-644613259
Summary of the change:
- Remove most of the short names (i, n, m, d, b) and use more informative
ones instead.
- Added comments between important code
alexwong edited a comment on issue #5835:
URL: https://github.com/apache/incubator-tvm/issues/5835#issuecomment-646220264
That makes sense. I'm wondering if you're updating the parser to support
that fork of Darknet and it seems to have diverged slightly from the upstream
master, it could
alexwong edited a comment on issue #5835:
URL: https://github.com/apache/incubator-tvm/issues/5835#issuecomment-646220264
That makes sense. I'm wondering if you're updating the parser to support
that fork of Darknet and it seems to have diverged slightly from master, it
could potentially
alexwong commented on issue #5835:
URL: https://github.com/apache/incubator-tvm/issues/5835#issuecomment-646220264
That makes sense. Do you have a rough idea of when you think you'll finish
the update? Thanks!
This is an
jwfromm commented on pull request #5845:
URL: https://github.com/apache/incubator-tvm/pull/5845#issuecomment-646216494
thanks for the fix, LGTM.
This is an automated message from the Apache Git Service.
To respond to the
mbrookhart opened a new pull request #5845:
URL: https://github.com/apache/incubator-tvm/pull/5845
@masahi
@jwfromm discovered an issue with #5755 , infer_value chokes on ops with
multiple outputs. I already knew this for Tuple, this adds a work around to
infer batch_norm with the
kevinthesun commented on a change in pull request #5844:
URL: https://github.com/apache/incubator-tvm/pull/5844#discussion_r442390568
##
File path: topi/python/topi/vision/nms.py
##
@@ -326,30 +329,40 @@ def hybrid_nms(data, sorted_index, valid_count, indices,
batch_size,
maheshambule commented on pull request #5528:
URL: https://github.com/apache/incubator-tvm/pull/5528#issuecomment-646202822
@anijain2305, it would be great to hear your feedback/review on this
proposed refactoring.
@u99127 Do you want to add further comments/suggestions here.
anijain2305 commented on pull request #5528:
URL: https://github.com/apache/incubator-tvm/pull/5528#issuecomment-646176715
@u99127 @maheshambule Are we following up on this?
This is an automated message from the Apache Git
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/master by this push:
new 082874c [Torch][Quantized] Fix
masahi merged pull request #5839:
URL: https://github.com/apache/incubator-tvm/pull/5839
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
yongwww commented on pull request #5844:
URL: https://github.com/apache/incubator-tvm/pull/5844#issuecomment-646139868
Tested with 2 random boxes (score_threshold=0, iou_threshold=0.6,
max_output_size=7) on my local env., the execution time of nms decreased to
0.003057119846343994
tqchen commented on issue #5841:
URL: https://github.com/apache/incubator-tvm/issues/5841#issuecomment-646135212
Please open a new trouble shooting thread on https://discuss.tvm.ai/
This is an automated message from the
tqchen commented on a change in pull request #5753:
URL: https://github.com/apache/incubator-tvm/pull/5753#discussion_r442344555
##
File path: python/tvm/runtime/module.py
##
@@ -41,6 +41,10 @@ def __init__(self, handle):
self.handle = handle
self._entry =
yongwww opened a new pull request #5844:
URL: https://github.com/apache/incubator-tvm/pull/5844
- modify nms to support symbolic max_output_size
- stop iou computation once get enough boxes
@kevinthesun @zhiics @icemelon9 @lixiaoquan
t-vi commented on pull request #5843:
URL: https://github.com/apache/incubator-tvm/pull/5843#issuecomment-646121900
@tqchen / @zhiics I think you're closest to this code.
This is an automated message from the Apache Git
t-vi opened a new pull request #5843:
URL: https://github.com/apache/incubator-tvm/pull/5843
In Python, generic objects (i.e. non-types/classes) inherit the `__dir__`
elements from their class.
This enable tab completion in interactive environments like Jupyter
notebooks.
zhanghaohit opened a new pull request #5842:
URL: https://github.com/apache/incubator-tvm/pull/5842
This PR, coupled with
[this](https://github.com/apache/incubator-tvm-vta/pull/9) on tvm-vta repo, is
the basic implementation of RFC #4958
Some notes:
- this is just a basic
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442174045
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
siju-samuel commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442164092
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
#
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442163343
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442162253
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
siju-samuel commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442146948
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
#
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442145084
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442145084
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
zhanghaohit opened a new pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9
This PR relates to this
[RFC](https://github.com/apache/incubator-tvm/issues/5840).
Main changes are:
- OpenCL driver
- intelfocl implementation for VTA
- add ALU MUL and
agdkyang opened a new issue #5841:
URL: https://github.com/apache/incubator-tvm/issues/5841
When I use tvm at arm server, find the error:
: CommandLine Error: Option 'aarch64-enable-ccmp' registered more than once!
LLVM ERROR: inconsistency in registered CommandLine options
masahi commented on a change in pull request #5839:
URL: https://github.com/apache/incubator-tvm/pull/5839#discussion_r442127672
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -595,15 +601,18 @@ def _impl(inputs, input_types):
return
zhanghaohit opened a new issue #5840:
URL: https://github.com/apache/incubator-tvm/issues/5840
# Motivation
Cloud devices are more powerful than Edge devices, which provides higher
computation capabilities for deep learning workloads. For example, for the VTA
core, with Cloud
siju-samuel commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442033597
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -1755,12 +1809,21 @@ def _convert_data_type(input_type):
return "int8"
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442105064
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -1733,12 +1780,19 @@ def _convert_dtype_value(val):
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442105064
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -1733,12 +1780,19 @@ def _convert_dtype_value(val):
siju-samuel commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442088235
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
#
siju-samuel edited a comment on issue #5835:
URL: https://github.com/apache/incubator-tvm/issues/5835#issuecomment-645889680
@alexwong This error is because the `network` and `layer` datastructure is
not same between master and tvmbranch. So the parsing have issues.
Im currently
siju-samuel commented on issue #5835:
URL: https://github.com/apache/incubator-tvm/issues/5835#issuecomment-645889680
@alexwong This error is because the `network` and `layer` datastructure is
not same. So the parsing have issues.
Im currently updating the whole code based on
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442079677
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442079677
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
t-vi commented on a change in pull request #5834:
URL: https://github.com/apache/incubator-tvm/pull/5834#discussion_r442079677
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -115,64 +115,70 @@ def inplace_add_to_add(op_name):
return False
+
# operator
1 - 100 of 109 matches
Mail list logo