huochaitiantang opened a new pull request #6181:
URL: https://github.com/apache/incubator-tvm/pull/6181
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request is submitted, please request
junrushao1994 commented on a change in pull request #6152:
URL: https://github.com/apache/incubator-tvm/pull/6152#discussion_r463400748
##
File path: src/relay/transforms/to_basic_block_normal_form.cc
##
@@ -0,0 +1,271 @@
+/*
+ * Licensed to the Apache Software Foundation
lixiaoquan opened a new pull request #6180:
URL: https://github.com/apache/incubator-tvm/pull/6180
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
tqchen commented on a change in pull request #6154:
URL: https://github.com/apache/incubator-tvm/pull/6154#discussion_r463332373
##
File path: src/support/hexdump.h
##
@@ -0,0 +1,45 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
tqchen commented on issue #6179:
URL: https://github.com/apache/incubator-tvm/issues/6179#issuecomment-666769790
cc @jroesch @MarisaKirisame @junrushao1994 @antinucleon
This is an automated message from the Apache Git
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 a2c6cb6 Fix incorrect function
tqchen merged pull request #6172:
URL: https://github.com/apache/incubator-tvm/pull/6172
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 issue #6179:
URL: https://github.com/apache/incubator-tvm/issues/6179#issuecomment-70447
An additional note is that we should change the grad verification to use
numerical grad checking instead of Pytorch
tqchen opened a new issue #6179:
URL: https://github.com/apache/incubator-tvm/issues/6179
https://ci.tvm.ai/blue/organizations/jenkins/tvm/detail/PR-6173/3/pipeline
This is an automated message from the Apache Git
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 64e08db [BYOC] Retire the example json
tqchen merged pull request #6177:
URL: https://github.com/apache/incubator-tvm/pull/6177
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 removed a comment on pull request #6152:
URL: https://github.com/apache/incubator-tvm/pull/6152#issuecomment-665942064
Ping me if the PR is ready to review :-)
This is an automated message from the Apache Git
jroesch commented on a change in pull request #6162:
URL: https://github.com/apache/incubator-tvm/pull/6162#discussion_r463206316
##
File path: src/parser/parser.cc
##
@@ -542,39 +496,60 @@ class Parser {
*/
template
Array ParseSequence(TokenType start, TokenType
areusch commented on issue #6175:
URL: https://github.com/apache/incubator-tvm/issues/6175#issuecomment-01707
this should be addressed by #6145
This is an automated message from the Apache Git Service.
To respond to the
electriclilies commented on a change in pull request #6174:
URL: https://github.com/apache/incubator-tvm/pull/6174#discussion_r463173545
##
File path: docs/dev/hybrid_script.rst
##
@@ -91,3 +91,10 @@ Math Intrinsics
So far, these math intrinsics, ``log``, ``exp``,
tqchen commented on issue #6175:
URL: https://github.com/apache/incubator-tvm/issues/6175#issuecomment-666540766
cc @liangfu @areusch
This is an automated message from the Apache Git Service.
To respond to the message,
xijiz opened a new issue #6178:
URL: https://github.com/apache/incubator-tvm/issues/6178
Hi,
I am using TVM Golang API for neural model inference. However, I can not
import the compiled binary package `gotvm.a` in my code. The environment
information as follows:
- Golang 1.4.0
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 a26ac93 [AutoScheduler] Improve doc string (#6176)
add 68e21fe Buffer logger assert removed (#6147)
tqchen commented on pull request #6147:
URL: https://github.com/apache/incubator-tvm/pull/6147#issuecomment-666524830
Thanks @ANSHUMAN87 @spectrometerHBH
This is an automated message from the Apache Git Service.
To respond
tqchen merged pull request #6147:
URL: https://github.com/apache/incubator-tvm/pull/6147
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
ANSHUMAN87 commented on a change in pull request #6162:
URL: https://github.com/apache/incubator-tvm/pull/6162#discussion_r463101025
##
File path: src/parser/meta_ref.cc
##
@@ -0,0 +1,104 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more
tqchen merged pull request #6176:
URL: https://github.com/apache/incubator-tvm/pull/6176
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 760a547 [TF] Fix some shape mismatches between TF and Relay (#6166)
add a26ac93 [AutoScheduler]
zhiics opened a new pull request #6177:
URL: https://github.com/apache/incubator-tvm/pull/6177
The example json runtime was introduced for demo purpose. Since we have
already implemented a real json runtime, this one should be removed now. This
would also unblock #6131
@comaniac
zhiics commented on a change in pull request #6174:
URL: https://github.com/apache/incubator-tvm/pull/6174#discussion_r463103326
##
File path: docs/dev/hybrid_script.rst
##
@@ -91,3 +91,10 @@ Math Intrinsics
So far, these math intrinsics, ``log``, ``exp``, ``sigmoid``,
gussmith23 commented on pull request #5812:
URL: https://github.com/apache/incubator-tvm/pull/5812#issuecomment-666479892
@tqchen looking for your input on testing (or feel free to point us to
someone else who could advise us!)
@hypercubestart is working on making the BYODT tests
zhiics commented on pull request #6131:
URL: https://github.com/apache/incubator-tvm/pull/6131#issuecomment-666460584
Yeah, one quick thing I can do is to retire the example runtime since we
have a real json runtime now. This example is not really use any more. I can
send a PR later. cc
ANSHUMAN87 commented on pull request #6066:
URL: https://github.com/apache/incubator-tvm/pull/6066#issuecomment-666461607
I think we can go ahead and merge the PR, as most of the scenarios are
handled.
I will keep loop unswitching as open point, once it is handled will raise
new PR for
mbaret commented on pull request #6171:
URL: https://github.com/apache/incubator-tvm/pull/6171#issuecomment-666399486
This has failed to pass CI 4 times now with different errors that don't
appear related to this patch. Is there a CI issue at the moment?
gussmith23 commented on pull request #5812:
URL: https://github.com/apache/incubator-tvm/pull/5812#issuecomment-666398623
Thanks, Theo! We'll be making heavy use of posits to test the framework, so
we'll be sure to use the right configurations.
Gus
On Thu, Jul 30, 2020,
spectrometerHBH commented on pull request #6147:
URL: https://github.com/apache/incubator-tvm/pull/6147#issuecomment-666367510
LGTM
This is an automated message from the Apache Git Service.
To respond to the message, please
ANSHUMAN87 commented on pull request #6147:
URL: https://github.com/apache/incubator-tvm/pull/6147#issuecomment-666366016
@tqchen , @spectrometerHBH : In case there is no further comment. May be we
can merge this one. TIA!
ANSHUMAN87 commented on pull request #6066:
URL: https://github.com/apache/incubator-tvm/pull/6066#issuecomment-666365123
> 0: I dont think a pass have to handle all cases for it to be merged. We
can improve upon it incrementally.
> 1: About loop unswitching, detecting invariant is very
MarisaKirisame commented on a change in pull request #6152:
URL: https://github.com/apache/incubator-tvm/pull/6152#discussion_r462680291
##
File path: src/relay/transforms/to_a_normal_form.cc
##
@@ -50,10 +50,17 @@ Scope LCA(Scope lhs, Scope rhs) {
return lhs;
}
Ravenwater commented on pull request #5812:
URL: https://github.com/apache/incubator-tvm/pull/5812#issuecomment-666289392
@gussmith23 the posit standard is moving towards posit<8,2>, posit<16,2>,
posit<32,2>, posit<64,2> specifically to make conversions better, faster,
cheaper.
merrymercy commented on pull request #6176:
URL: https://github.com/apache/incubator-tvm/pull/6176#issuecomment-666262824
cc @jcf94 @comaniac @jroesch @tqchen
This is an automated message from the Apache Git Service.
To
merrymercy opened a new pull request #6176:
URL: https://github.com/apache/incubator-tvm/pull/6176
Improve the doc strings in the header files and python interface
This is an automated message from the Apache Git Service.
To
lhutton1 commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462844943
##
File path: docs/deploy/arm_compute_lib.rst
##
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to
ACL to use
leandron commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462844056
##
File path: docs/deploy/arm_compute_lib.rst
##
@@ -42,6 +60,19 @@ to compile an ACL module on an x86 machine and then run the
module on a
leandron commented on pull request #6167:
URL: https://github.com/apache/incubator-tvm/pull/6167#issuecomment-666226823
cc @anijain2305 @u99127 @FrozenGene
This is an automated message from the Apache Git Service.
To respond
lhutton1 commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462841020
##
File path: docs/deploy/arm_compute_lib.rst
##
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to
ACL to use
leandron commented on pull request #6167:
URL: https://github.com/apache/incubator-tvm/pull/6167#issuecomment-666226823
cc @anijain2305 @u99127 @FrozenGene
This is an automated message from the Apache Git Service.
To respond
tqchen opened a new pull request #6173:
URL: https://github.com/apache/incubator-tvm/pull/6173
cc @jroesch @electriclilies
This is an automated message from the Apache Git Service.
To respond to the message, please log on
vinx13 opened a new pull request #6172:
URL: https://github.com/apache/incubator-tvm/pull/6172
The signature in the header is inconsistent with the implementation in
`memory.cc` file
This is an automated message from the
electriclilies opened a new pull request #6174:
URL: https://github.com/apache/incubator-tvm/pull/6174
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
jroesch commented on a change in pull request #6162:
URL: https://github.com/apache/incubator-tvm/pull/6162#discussion_r462735811
##
File path: tests/python/relay/test_ir_parser2.py
##
@@ -1,891 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
Review
zhanghaohit commented on a change in pull request #6124:
URL: https://github.com/apache/incubator-tvm/pull/6124#discussion_r462690226
##
File path: tests/python/relay/test_pass_annotation.py
##
@@ -309,6 +309,76 @@ def test_visitor_annotation():
test_visitor_annotation()
MarisaKirisame commented on a change in pull request #6152:
URL: https://github.com/apache/incubator-tvm/pull/6152#discussion_r462680291
##
File path: src/relay/transforms/to_a_normal_form.cc
##
@@ -50,10 +50,17 @@ Scope LCA(Scope lhs, Scope rhs) {
return lhs;
}
tkonolige commented on pull request #6131:
URL: https://github.com/apache/incubator-tvm/pull/6131#issuecomment-665960679
One of the failing tests is `tests/python/relay/test_external_runtime.py`.
You can play around with it to try and debug.
mbrookhart commented on a change in pull request #6124:
URL: https://github.com/apache/incubator-tvm/pull/6124#discussion_r462608830
##
File path: src/relay/transforms/device_annotation.cc
##
@@ -414,22 +427,23 @@ class DeviceInfo {
void VisitExpr_(const TupleGetItemNode*
jroesch commented on pull request #6131:
URL: https://github.com/apache/incubator-tvm/pull/6131#issuecomment-666124551
I pinged @zhiics since he is the owner afaik of this code, he said he would
look at it tomorrow.
This
mikeseven opened a new issue #6175:
URL: https://github.com/apache/incubator-tvm/issues/6175
The example runtime bundle_deploy builds demo_static but not demo_dynamic
due to runtime.c that has moved.
This is an automated
gussmith23 commented on a change in pull request #5812:
URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r462635059
##
File path: src/tir/transforms/lower_custom_datatypes.cc
##
@@ -97,6 +97,29 @@ class CustomDatatypesLowerer : public StmtExprMutator {
remotego commented on pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-665845575
> thanks @remotego @liangfu @pasqoc for the insightful comments. I think
that all opinions expressed are very valid!
>
> So far our approach to naming VTA target has
junrushao1994 commented on pull request #6152:
URL: https://github.com/apache/incubator-tvm/pull/6152#issuecomment-665942064
Ping me if the PR is ready to review :-)
This is an automated message from the Apache Git Service.
ANSHUMAN87 commented on a change in pull request #6162:
URL: https://github.com/apache/incubator-tvm/pull/6162#discussion_r462751589
##
File path: python/tvm/parser/__init__.py
##
@@ -24,4 +24,5 @@ def parse_expr(source):
return _ffi_api.ParseExpr("string", source)
def
remotego edited a comment on pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-665845575
> thanks @remotego @liangfu @pasqoc for the insightful comments. I think
that all opinions expressed are very valid!
>
> So far our approach to naming VTA
zhiics commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462526176
##
File path: docs/deploy/arm_compute_lib.rst
##
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to
ACL to use
yzhliu commented on pull request #6054:
URL: https://github.com/apache/incubator-tvm/pull/6054#issuecomment-666083649
Please check the ci failure, otherwise good to me.
This is an automated message from the Apache Git
59 matches
Mail list logo