ANSHUMAN87 commented on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649636006
@yzhliu : The issue is fixed indeed, Thanks!
I think it would be good if we add the issue test case as well.
--> expr = (((x0 - floordiv((0 - (x1*5)), 2)) -
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445653492
##
File path: src/runtime/contrib/json/json_runtime.h
##
@@ -0,0 +1,267 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ *
ANSHUMAN87 edited a comment on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649636006
@yzhliu : The original issue is fixed indeed, Thanks!
I think it would be good if we add the issue test case as well.
--> expr = (((x0 - floordiv((0 -
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 7830561 [Relay][Vm] Some performance improvement to VM (#5901)
add 2a03d24 Update install.rst (#5858)
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 2a03d24 Update install.rst (#5858)
add 6d59ed4 Two small fixes to AMDCPU codegen for LLVM 10+ and ROCm
tqchen merged pull request #5920:
URL: https://github.com/apache/incubator-tvm/pull/5920
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
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445649806
##
File path: tests/python/relay/test_json_runtime.py
##
@@ -0,0 +1,625 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or
yzhliu commented on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649705664
@ANSHUMAN87 good catch, this is what the argument `step` for I added in #5618
This is an automated message
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 074a07e CUDA device API & VerifyGPUCode pass update (#5898)
add 7830561 [Relay][Vm] Some performance
zhiics merged pull request #5901:
URL: https://github.com/apache/incubator-tvm/pull/5901
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
zhiics commented on pull request #5901:
URL: https://github.com/apache/incubator-tvm/pull/5901#issuecomment-649601265
Thanks @icemelon9
This is an automated message from the Apache Git Service.
To respond to the message,
tqchen commented on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649615620
Thanks @yzhliu , seems we need a different testcase, that uses a truncdiv
but still triggers DivModeCompatibleTo
tqchen commented on a change in pull request #5924:
URL: https://github.com/apache/incubator-tvm/pull/5924#discussion_r445642433
##
File path: src/arith/rewrite_simplify.cc
##
@@ -722,8 +728,15 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
FloorDivNode* op) {
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445655112
##
File path: src/relay/backend/graph_runtime_codegen.cc
##
@@ -661,6 +660,8 @@ struct Handler> {
writer->WriteObjectKeyValue(k,
t-vi commented on pull request #5920:
URL: https://github.com/apache/incubator-tvm/pull/5920#issuecomment-649657507
@tqchen Yeah, so the background to this is that the recent release of ROCm
3.5 brings rather sweeping changes (changing the compiler backend for the HIP
compilation among
tqchen edited a comment on pull request #5924:
URL: https://github.com/apache/incubator-tvm/pull/5924#issuecomment-649619450
Thanks @jcf94 we should add a testcase to test_arith_rewrite_simplify, by
constructing the case and
- verify each of the rule added in this PR.
- Use
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445666228
##
File path: src/runtime/metadata_module.cc
##
@@ -48,15 +48,22 @@ class MetadataModuleNode : public ModuleNode {
public:
tqchen commented on pull request #5920:
URL: https://github.com/apache/incubator-tvm/pull/5920#issuecomment-649618356
NOTE: using runtime detection of rocm features will only work if we are
building on the same machine and won't work for cross compilation. While it is
OK for now, let us
comaniac opened a new pull request #5926:
URL: https://github.com/apache/incubator-tvm/pull/5926
To reduce the overhead of runtime symbol lookup, we should only initialize
the runtime modules that include the symbol we need for executing this graph.
cc @zhiics @mbaret
mbaret commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445665730
##
File path: tests/python/relay/test_json_runtime.py
##
@@ -0,0 +1,625 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
mbaret commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445666219
##
File path: src/runtime/contrib/json/json_runtime.h
##
@@ -0,0 +1,267 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or
yzhliu opened a new pull request #5927:
URL: https://github.com/apache/incubator-tvm/pull/5927
#5922
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
tqchen commented on pull request #5826:
URL: https://github.com/apache/incubator-tvm/pull/5826#issuecomment-649616499
cc @icemelon9 please followup and manage this PR, @jroesch @electriclilies
please
tqchen edited a comment on pull request #5826:
URL: https://github.com/apache/incubator-tvm/pull/5826#issuecomment-649616499
cc @icemelon9 please followup and manage this PR, @jroesch @electriclilies
@lixiaoquan please
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445644835
##
File path: src/relay/backend/contrib/codegen_json/codegen_json.h
##
@@ -0,0 +1,353 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF)
comaniac commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445655112
##
File path: src/relay/backend/graph_runtime_codegen.cc
##
@@ -661,6 +660,8 @@ struct Handler> {
writer->WriteObjectKeyValue(k,
tqchen commented on pull request #5924:
URL: https://github.com/apache/incubator-tvm/pull/5924#issuecomment-649619450
@jcf94 we should add a testcase to test_arith_rewrite_simplify, by
constructing the case and verify the rules you have worked. Use `isinstance(x,
tvm.ir.Ramp)` to assert
ANSHUMAN87 edited a comment on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649639015
@tqchen, @yzhliu : I have one concern here(However not related to this PR).
As you see the expr below:
expr = (((x0 - floordiv((0 - (x1*5)), 2)) - 1) +
mbaret commented on a change in pull request #5919:
URL: https://github.com/apache/incubator-tvm/pull/5919#discussion_r445662045
##
File path: src/relay/backend/contrib/codegen_json/codegen_json.h
##
@@ -0,0 +1,353 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF)
ANSHUMAN87 commented on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649639015
@tqchen, @yzhliu : I have one concern here.
As you see the expr below:
expr = (((x0 - floordiv((0 - (x1*5)), 2)) - 1) + floordiv((37 + ((x1 +
7)*-5)), 2))
tmoreau89 commented on pull request #5858:
URL: https://github.com/apache/incubator-tvm/pull/5858#issuecomment-64967
thank you @badenh your changes have been merged
This is an automated message from the Apache Git
tmoreau89 merged pull request #5858:
URL: https://github.com/apache/incubator-tvm/pull/5858
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
tqchen commented on pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922#issuecomment-649726080
@yzhliu please also send a patch to v0.6
This is an automated message from the Apache Git Service.
To
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649870756
Those two PRs plus this change to the script fixes the issue for me:
```
import tvm
from tvm import relay
from tvm.relay.dataflow_pattern import *
import
comaniac commented on a change in pull request #5930:
URL: https://github.com/apache/incubator-tvm/pull/5930#discussion_r445892435
##
File path: tests/python/relay/test_dataflow_pattern.py
##
@@ -1133,6 +1133,37 @@ def test_partition_double_batchnorm():
reference =
s1113950 commented on pull request #5456:
URL: https://github.com/apache/incubator-tvm/pull/5456#issuecomment-649922257
I was told to stop working on this until a later date while I was at OctoML,
and then my contract ended. Sorry, I forgot to mention that in a comment on
this PR .
s1113950 edited a comment on pull request #5456:
URL: https://github.com/apache/incubator-tvm/pull/5456#issuecomment-649922257
I was told to stop working on this until a later date while I was at OctoML,
and then my contract with OctoML ended. Sorry, I forgot to mention that in a
comment
liangfu commented on pull request #5456:
URL: https://github.com/apache/incubator-tvm/pull/5456#issuecomment-649874396
Hi @s1113950, is there any update lately?
This is an automated message from the Apache Git Service.
To
areusch commented on pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#issuecomment-649874830
hi @liangfu, I posted up an RFC about this here:
https://discuss.tvm.ai/t/rfc-misra-c-changes-for-rpc-support/7098/2
tqchen merged pull request #5929:
URL: https://github.com/apache/incubator-tvm/pull/5929
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 16c5d4d [BACKPORT-0.6][Bugfix][Arith] keep div_mode during floordiv
simplify (#5922)
add 318d268
mbrookhart edited a comment on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649870756
Those two PRs plus this change to the script fixes the issue for me:
```
import tvm
from tvm import relay
from tvm.relay.dataflow_pattern import *
liangfu commented on pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#issuecomment-649886775
Thanks for quick response and the comprehensive RFC. Let's discuss the the
proposed features in the post.
This is an automated email from the ASF dual-hosted git repository.
liuyizhi pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 6d59ed4 Two small fixes to AMDCPU codegen for LLVM 10+ and ROCm 3.5+
(#5920)
add 16c5d4d
yzhliu merged pull request #5922:
URL: https://github.com/apache/incubator-tvm/pull/5922
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
comaniac commented on a change in pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#discussion_r445736912
##
File path: cmake/modules/contrib/ACL.cmake
##
@@ -0,0 +1,68 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
trevor-m commented on a change in pull request #5857:
URL: https://github.com/apache/incubator-tvm/pull/5857#discussion_r445798573
##
File path: tests/python/relay/test_op_level5.py
##
@@ -270,8 +270,8 @@ def verify_get_valid_counts(dshape, score_threshold,
id_index,
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649789497
I'll try to reproduce, thanks for filing the issue!
This is an automated message from the Apache Git
comaniac commented on a change in pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#discussion_r445810621
##
File path: cmake/modules/contrib/ACL.cmake
##
@@ -0,0 +1,68 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
comaniac commented on a change in pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#discussion_r445810283
##
File path: src/relay/backend/contrib/acl/README.md
##
@@ -0,0 +1,111 @@
+
+
+# Relay Arm Compute Library Integration
Review comment:
tqchen commented on pull request #5910:
URL: https://github.com/apache/incubator-tvm/pull/5910#issuecomment-649803983
Thanks @jinboci Please do the experiments locally first before sending the
PR upstream, since the CI resources is pretty limited atm.
tqchen closed pull request #5910:
URL: https://github.com/apache/incubator-tvm/pull/5910
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
liangfu commented on pull request #5921:
URL: https://github.com/apache/incubator-tvm/pull/5921#issuecomment-649873219
@areusch Thanks for your valuable contribution. Since this is a rather big
change that might affect many existing users, would you please send an RFC for
discussion
comaniac commented on a change in pull request #5931:
URL: https://github.com/apache/incubator-tvm/pull/5931#discussion_r445901105
##
File path: src/relay/transforms/eliminate_common_subexpr.cc
##
@@ -58,27 +58,52 @@ class CommonSubexprEliminator : public ExprMutator {
comaniac commented on a change in pull request #5931:
URL: https://github.com/apache/incubator-tvm/pull/5931#discussion_r445901105
##
File path: src/relay/transforms/eliminate_common_subexpr.cc
##
@@ -58,27 +58,52 @@ class CommonSubexprEliminator : public ExprMutator {
mbrookhart commented on a change in pull request #5930:
URL: https://github.com/apache/incubator-tvm/pull/5930#discussion_r445915192
##
File path: tests/python/relay/test_dataflow_pattern.py
##
@@ -1133,6 +1133,37 @@ def test_partition_double_batchnorm():
reference =
comaniac commented on a change in pull request #5930:
URL: https://github.com/apache/incubator-tvm/pull/5930#discussion_r445919066
##
File path: tests/python/relay/test_dataflow_pattern.py
##
@@ -1133,6 +1133,37 @@ def test_partition_double_batchnorm():
reference =
jroesch opened a new pull request #5932:
URL: https://github.com/apache/incubator-tvm/pull/5932
This PR implements a pure C++ parser for Relay's text format and starts to
lay ground work for improved error reporting and full program parsing work that
I will send an RFC for sometime next
mbrookhart opened a new pull request #5931:
URL: https://github.com/apache/incubator-tvm/pull/5931
@MarisaKirisame @comaniac
Add TupleGetItem to CSE. Helps solve the issue in #5928
This is an automated message
junrushao1994 commented on a change in pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917#discussion_r445941711
##
File path: .gitignore
##
@@ -196,6 +196,7 @@ tvm_t.*
.python_history
.pytest_cache
.local
+cmake-build-debug
Review comment:
icemelon9 commented on a change in pull request #5826:
URL: https://github.com/apache/incubator-tvm/pull/5826#discussion_r445779288
##
File path: python/tvm/relay/op/dyn/transform.py
##
@@ -0,0 +1,74 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
lhutton1 commented on a change in pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#discussion_r445783066
##
File path: cmake/modules/contrib/ACL.cmake
##
@@ -0,0 +1,68 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
trevor-m commented on a change in pull request #5857:
URL: https://github.com/apache/incubator-tvm/pull/5857#discussion_r445799816
##
File path: tests/python/relay/test_op_level5.py
##
@@ -270,8 +270,8 @@ def verify_get_valid_counts(dshape, score_threshold,
id_index,
anijain2305 commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445827227
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -2566,17 +2613,27 @@ def convert_quantize(self, op):
input_tensors =
comaniac commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649819741
Ah apparently I was wrong. MobileNet has residual connections...I see. So
`%20` and `%33` are partitioned to a function. In this case "another `%20`" is
rejected to be
tqchen edited a comment on pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917#issuecomment-649748029
cc @vinx13 @Hzfengsy @spectrometerHBH please also help to take a look, we
can proceed to merge after reviews by a few more eyes
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 802f055 [BACKPORT-0.6][Bugfix][Arith] keep
tqchen merged pull request #5927:
URL: https://github.com/apache/incubator-tvm/pull/5927
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
comaniac opened a new issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928
Pointed out by @trevor-m, the following case that uses a `batch_norm ->
get(0)` to match MobileNet V2, but some subgraphs were failed to be matched and
partitioned.
```python
import tvm
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649816992
It should probably just be:
```
%34 = add(%32, %21)
```
To get the behavior you want. So...Relay level CSE? I'm going to double
check the partition rejection
mbrookhart opened a new pull request #5930:
URL: https://github.com/apache/incubator-tvm/pull/5930
@comaniac
While investigating #5928, I discovered an issue where the pattern language
would rewrite expressions used outside of the pattern, this prevents that
issue, but doesn't fix
tqchen commented on pull request #5925:
URL: https://github.com/apache/incubator-tvm/pull/5925#issuecomment-649753751
Thanks @giuseros can you add a regression test case as per
https://tvm.apache.org/docs/contribute/code_review.html#ensure-test-coverage?
trevor-m commented on a change in pull request #5857:
URL: https://github.com/apache/incubator-tvm/pull/5857#discussion_r445799816
##
File path: tests/python/relay/test_op_level5.py
##
@@ -270,8 +270,8 @@ def verify_get_valid_counts(dshape, score_threshold,
id_index,
trevor-m commented on a change in pull request #5857:
URL: https://github.com/apache/incubator-tvm/pull/5857#discussion_r445798573
##
File path: tests/python/relay/test_op_level5.py
##
@@ -270,8 +270,8 @@ def verify_get_valid_counts(dshape, score_threshold,
id_index,
tqchen edited a comment on pull request #5910:
URL: https://github.com/apache/incubator-tvm/pull/5910#issuecomment-649803983
Thanks @jinboci Please do the experiments locally first before sending the
PR upstream, since the CI resources is pretty limited
atm. Because the cuda runtime
icemelon9 commented on pull request #5826:
URL: https://github.com/apache/incubator-tvm/pull/5826#issuecomment-649765936
@mbrookhart Since we separate the static and dynamic reshape in this pr, we
should remove the `Optional` in the `ReshapeAttrs` correspondingly.
comaniac commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649814547
Yeah it should not be a case for MobileNet model. MobileNet model should be
a single dataflow pipeline without branches and residual connections.
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649815056
Found it:
The original model has this:
```
%20 = nn.batch_norm(%19, meta[relay.Constant][26] /* ty=Tensor[(24),
float32] */ /* ty=Tensor[(24), float32] */,
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649836440
Yes. I think the right solution is CSE, but that is at lot of work.
This is an automated message from the
tqchen commented on pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917#issuecomment-649748029
cc @vinx13 @Hzfengsy @spectrometerHBH please also help to take a look, we
can proceed to merge after a few more eyes
comaniac opened a new pull request #5929:
URL: https://github.com/apache/incubator-tvm/pull/5929
To better understand which ops are missing in the MXNet frontend, it would
be better to traverse an entire model and provide a list of unsupported ops and
their counts instead of throwing an
comaniac commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649824271
I guess an ideal solution would be trying to figure out those two matches
are duplicated and reuse the first partitioned function for the second match?
But this would look
tqchen commented on pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#issuecomment-649750307
let us consider expand the name acl to arm_compute_lib or some other
alternatives, since ACL means different things to ML/NLP audiences
lhutton1 commented on pull request #5915:
URL: https://github.com/apache/incubator-tvm/pull/5915#issuecomment-649796679
> let us consider expand the name acl to arm_compute_lib or some other
alternatives, since ACL means different things to ML/NLP audiences
I'd be happy to change
mbrookhart commented on issue #5928:
URL: https://github.com/apache/incubator-tvm/issues/5928#issuecomment-649810207
This isn't making much sense to me, it looks like a few of the batch_norm
call nodes are duplicated, i.e., exactly the same object. The partition pass is
refusing to fuse
merrymercy merged pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917
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
merrymercy commented on a change in pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917#discussion_r445980708
##
File path: .gitignore
##
@@ -196,6 +196,7 @@ tvm_t.*
.python_history
.pytest_cache
.local
+cmake-build-debug
Review comment:
It is
merrymercy commented on a change in pull request #5917:
URL: https://github.com/apache/incubator-tvm/pull/5917#discussion_r445980708
##
File path: .gitignore
##
@@ -196,6 +196,7 @@ tvm_t.*
.python_history
.pytest_cache
.local
+cmake-build-debug
Review comment:
It is
This is an automated email from the ASF dual-hosted git repository.
lmzheng 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 96bf271 [TE] Add LegalizeInvalidAttach
anijain2305 commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445326823
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -2445,6 +2467,112 @@ def test_forward_qnn_mobilenet_v3_net():
anijain2305 commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445326083
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1605,7 +1645,7 @@ def convert_fully_connected(self, op):
# weight tensor
anijain2305 commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445326022
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -262,21 +298,25 @@ def get_tensor_value(self, tensor_wrapper):
except
badenh commented on pull request #5858:
URL: https://github.com/apache/incubator-tvm/pull/5858#issuecomment-649428998
Yes, fixed the missing item now
This is an automated message from the Apache Git Service.
To respond to
badenh opened a new pull request #5923:
URL: https://github.com/apache/incubator-tvm/pull/5923
editorial pass with corrections
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request
kazum commented on a change in pull request #5857:
URL: https://github.com/apache/incubator-tvm/pull/5857#discussion_r445411686
##
File path: tests/python/relay/test_op_level5.py
##
@@ -270,8 +270,8 @@ def verify_get_valid_counts(dshape, score_threshold,
id_index,
jcf94 opened a new pull request #5924:
URL: https://github.com/apache/incubator-tvm/pull/5924
This pr is part of #5883 , fix for the rewrite_simplify error when doing
vectorized cooperative fetching in some cases.
Code generated with bug is shown like this:
```
siju-samuel commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445531482
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -258,15 +260,18 @@ def get_tensors(self, tensors_idx_list):
assert
remotego commented on a change in pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#discussion_r445324802
##
File path: src/intelfocl/AOCLUtils/opencl.h
##
@@ -0,0 +1,122 @@
+// Copyright (C) 2013-2018 Altera Corporation, San Jose, California, USA. All
masahi commented on issue #5809:
URL: https://github.com/apache/incubator-tvm/issues/5809#issuecomment-649246713
This sounds like you need polyhedral model?
This is an automated message from the Apache Git Service.
To
anijain2305 commented on a change in pull request #5848:
URL: https://github.com/apache/incubator-tvm/pull/5848#discussion_r445355375
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -262,21 +298,25 @@ def get_tensor_value(self, tensor_wrapper):
except
1 - 100 of 105 matches
Mail list logo