CaptainDuke commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677961390
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we av
sunjiweiswift commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r678011784
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].
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 496f10b [Frontend][TENSORFLOW] Add support for unpack with dim 0
after tensorlist stack (#8558)
add 5a96a61 [Bugfix
jcf94 merged pull request #8530:
URL: https://github.com/apache/tvm/pull/8530
--
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.
To unsubscribe, e-mail: commits-unsubscr...@
huajsj commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677986161
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].push_ba
yzhliu commented on pull request #8434:
URL: https://github.com/apache/tvm/pull/8434#issuecomment-888008179
Great work @mbrookhart any update on this PR?
--
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 t
masahi opened a new pull request #8571:
URL: https://github.com/apache/tvm/pull/8571
A follow-up to https://github.com/apache/tvm/pull/8466
Hetero-dtype is supported per discussion
https://github.com/apache/tvm/pull/8466#discussion_r669836272
@tqchen @vinx13 @yzh119
--
Thi
CaptainDuke commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677961390
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we av
CaptainDuke commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677961390
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we av
CaptainDuke commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677961390
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we av
hogepodge commented on pull request #8382:
URL: https://github.com/apache/tvm/pull/8382#issuecomment-887988579
Regardless, if this is merged it needs to be called out in the developer
docs to encourage adoption.
--
This is an automated message from the Apache Git Service.
To respond to t
sunjiweiswift commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677951747
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].
sunjiweiswift commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677951747
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].
hogepodge commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887986659
I'm not sure I envisioned the tracking issue number/link be explicitly
placed into the RFC. The tracking issue referencing back to the RFC PR and and
RFC itself seems like it wou
hogepodge commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677945727
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo apt-ge
hogepodge commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677945727
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo apt-ge
huajsj commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677939968
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -139,6 +156,30 @@ void GraphExecutor::SetInputZeroCopy(int index, DLTensor*
data_ref) {
huajsj commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677939110
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].push_ba
huajsj commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677938511
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -139,6 +156,30 @@ void GraphExecutor::SetInputZeroCopy(int index, DLTensor*
data_ref) {
sunjiweiswift commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r677909040
##
File path: src/runtime/graph_executor/graph_executor.cc
##
@@ -139,6 +156,30 @@ void GraphExecutor::SetInputZeroCopy(int index, DLTensor*
data_ref)
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 8954968 Fix #8510 (#8511)
add 496f10b [Frontend][TENSORFLOW] Add support for unpack with dim 0
after tensorlist st
tqchen merged pull request #8558:
URL: https://github.com/apache/tvm/pull/8558
--
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.
To unsubscribe, e-mail: commits-unsubscr...
tqchen commented on pull request #8570:
URL: https://github.com/apache/tvm/pull/8570#issuecomment-887938514
Thanks @chanwutk . This would change the general serialization format and
would need a bit more discussion. If we need the additional information for say
visualizer, we could have an
chanwutk opened a new pull request #8570:
URL: https://github.com/apache/tvm/pull/8570
--
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.
To unsubscribe, e-mail: commits-uns
chanwutk closed pull request #8569:
URL: https://github.com/apache/tvm/pull/8569
--
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.
To unsubscribe, e-mail: commits-unsubscr.
AndrewZhaoLuo commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677894165
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo ap
hogepodge commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677891039
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo apt-ge
hogepodge commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677890790
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo apt-ge
areusch commented on pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#issuecomment-887922573
@mehrdadh @gromero please take another look!
--
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 t
areusch commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677889527
##
File path: apps/microtvm/zephyr/template_project/microtvm_api_server.py
##
@@ -0,0 +1,533 @@
+import collections
+import fcntl
+import logging
+import os
+
chanwutk opened a new pull request #8569:
URL: https://github.com/apache/tvm/pull/8569
--
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.
To unsubscribe, e-mail: commits-uns
areusch commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677884779
##
File path: apps/microtvm/zephyr/template_project/microtvm_api_server.py
##
@@ -0,0 +1,673 @@
+# Licensed to the Apache Software Foundation (ASF) under one
areusch commented on pull request #8514:
URL: https://github.com/apache/tvm/pull/8514#issuecomment-887917082
@grant-arm i believe we have resolved the CI issue that broke this
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub a
areusch commented on a change in pull request #8514:
URL: https://github.com/apache/tvm/pull/8514#discussion_r677884162
##
File path: docker/install/ubuntu_install_vela.sh
##
@@ -0,0 +1,24 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
ganler closed pull request #8559:
URL: https://github.com/apache/tvm/pull/8559
--
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.
To unsubscribe, e-mail: commits-unsubscr...
areusch commented on a change in pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#discussion_r677882618
##
File path: docs/install/from_source.rst
##
@@ -73,6 +73,16 @@ linux operating systems, execute (in a terminal):
sudo apt-get update
sudo apt-get
areusch commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887914798
@comaniac i view the core data structures and interfaces as part of the
design-level documentation. i think they belong in Reference-level explanation.
see for example my RFC #8 --
AndrewZhaoLuo commented on pull request #8568:
URL: https://github.com/apache/tvm/pull/8568#issuecomment-887905702
cc @hogepodge
--
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 com
AndrewZhaoLuo opened a new pull request #8568:
URL: https://github.com/apache/tvm/pull/8568
Testing:
Ran `restview` on the doc and made sure it looked ok-ish.
Tested this on a sort-of-fresh M1 mac and can confirm these instructions
work.
--
This is an automated message from th
comaniac commented on a change in pull request #6:
URL: https://github.com/apache/tvm-rfcs/pull/6#discussion_r677866702
##
File path: rfcs/0001-AMP_pass.md
##
@@ -0,0 +1,137 @@
+- Feature Name: Automatic Mixed Precision Pass
+- Start Date: 2021-06-08
+- RFC PR: TODO
+- GitHub
areusch commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677865658
##
File path: apps/bundle_deploy/crt_config/crt_config.h
##
@@ -35,9 +35,9 @@
/*! Maximum supported arguments in generated functions */
#define TVM_CRT_MAX_
areusch commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677865293
##
File path: python/tvm/micro/project.py
##
@@ -0,0 +1,97 @@
+"""Defines glue wrappers around the Project API which mate to TVM
interfaces."""
+
+from ..con
u99127 commented on a change in pull request #6:
URL: https://github.com/apache/tvm-rfcs/pull/6#discussion_r677863248
##
File path: rfcs/0001-AMP_pass.md
##
@@ -0,0 +1,137 @@
+- Feature Name: Automatic Mixed Precision Pass
+- Start Date: 2021-06-08
+- RFC PR: TODO
+- GitHub Is
areusch commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677863154
##
File path: apps/microtvm/zephyr/template_project/microtvm_api_server.py
##
@@ -0,0 +1,673 @@
+# Licensed to the Apache Software Foundation (ASF) under one
areusch commented on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887894876
@tkonolige @guberti @mehrdadh please take another look and explicitly
approve if you're good w/ this
--
This is an automated message from the Apache Git Service.
To respond to the
areusch commented on a change in pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#discussion_r677862381
##
File path: rfcs/0008-microtvm-project-api.md
##
@@ -0,0 +1,509 @@
+- Feature Name: microtvm_project_api
+- Start Date: 2020-06-09
+- RFC PR: [apache/tvm-rfc
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 f2354ee Add a `--context-path` for build.sh, allowing to test
Dockerfiles (#8557)
add 8954968 Fix #8510 (#8511)
N
tqchen closed issue #8510:
URL: https://github.com/apache/tvm/issues/8510
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.
tqchen merged pull request #8511:
URL: https://github.com/apache/tvm/pull/8511
--
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.
To unsubscribe, e-mail: commits-unsubscr...
AndrewZhaoLuo commented on pull request #6:
URL: https://github.com/apache/tvm-rfcs/pull/6#issuecomment-887889315
Thanks for driving this review @comaniac. I'll get to this later in the week.
--
This is an automated message from the Apache Git Service.
To respond to the message, please lo
tkonolige opened a new pull request #8567:
URL: https://github.com/apache/tvm/pull/8567
I forgot to add USE_PAPI to config.cmake.
@mbrookhart @areusch
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
UR
gromero commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677838273
##
File path: apps/bundle_deploy/crt_config/crt_config.h
##
@@ -35,9 +35,9 @@
/*! Maximum supported arguments in generated functions */
#define TVM_CRT_MAX_
u99127 commented on pull request #8368:
URL: https://github.com/apache/tvm/pull/8368#issuecomment-887881904
this looks like it could do with another CI kicking after any updates you
want to make @ekalda
--
This is an automated message from the Apache Git Service.
To respond to the mess
areusch commented on issue #8417:
URL: https://github.com/apache/tvm/issues/8417#issuecomment-887879629
I agree let us re-enable the tests and see how they do in CI with 0.06
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub an
areusch commented on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887879286
@Mousius please take another look when you can and explicitly approve!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHu
u99127 commented on issue #8417:
URL: https://github.com/apache/tvm/issues/8417#issuecomment-887879229
Ok I've tried this for quite a few times this evening after having acquired
access to an m6g4xlarge instance - not sure if this is the same as CI
- Running with image version v
gromero edited a comment on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887842848
>> On generate_project method, and considering TVMC, my only comment is that
it should allow a project creation based also on MLF .tar, instead of only a
"live" executor.
gromero edited a comment on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887842848
>> On generate_project method, and considering TVMC, my only comment is that
it should allow a project creation based also on MLF .tar, instead of only a
"live" executor.
u99127 commented on pull request #8556:
URL: https://github.com/apache/tvm/pull/8556#issuecomment-887863126
@leandron - is there a need to check this usage via tvmc as well if this
changes ?
--
This is an automated message from the Apache Git Service.
To respond to the message, please
gromero edited a comment on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887842848
>> On generate_project method, and considering TVMC, my only comment is that
it should allow a project creation based also on MLF .tar, instead of only a
"live" executor.
gromero edited a comment on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887842848
>> On generate_project method, and considering TVMC, my only comment is that
it should allow a project creation based also on MLF .tar, instead of only a
"live" executor.
gromero commented on pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#issuecomment-887842848
>> On generate_project method, and considering TVMC, my only comment is that
it should allow a project creation based also on MLF .tar, instead of only a
"live" executor.
>I agree
mbrookhart commented on issue #8565:
URL: https://github.com/apache/tvm/issues/8565#issuecomment-887834981
:/ I don't see the removal of the hard-coded target in the PR we did.
https://github.com/apache/tvm/pull/7438/files
But I could have sworn it was in there. Perhaps we messed up
electriclilies edited a comment on issue #8565:
URL: https://github.com/apache/tvm/issues/8565#issuecomment-887832017
Yeah, this hardcode shouldn't be there. @mbrookhart and I definitely removed
it (or tried to)..
--
This is an automated message from the Apache Git Service.
To respond t
electriclilies commented on issue #8565:
URL: https://github.com/apache/tvm/issues/8565#issuecomment-887832017
Yeah, @mbrookhart and I definitely removed it (or tried to)..
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
gromero commented on a change in pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#discussion_r677795073
##
File path: rfcs/0008-microtvm-project-api.md
##
@@ -0,0 +1,518 @@
+- Feature Name: microtvm_project_api
+- Start Date: 2020-06-09
+- RFC PR: [apache/tvm-rfc
gromero commented on a change in pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#discussion_r677792274
##
File path: rfcs/0008-microtvm-project-api.md
##
@@ -0,0 +1,518 @@
+- Feature Name: microtvm_project_api
+- Start Date: 2020-06-09
+- RFC PR: [apache/tvm-rfc
gromero commented on a change in pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#discussion_r677790052
##
File path: rfcs/0008-microtvm-project-api.md
##
@@ -0,0 +1,518 @@
+- Feature Name: microtvm_project_api
+- Start Date: 2020-06-09
+- RFC PR: [apache/tvm-rfc
gromero commented on a change in pull request #8:
URL: https://github.com/apache/tvm-rfcs/pull/8#discussion_r677790052
##
File path: rfcs/0008-microtvm-project-api.md
##
@@ -0,0 +1,518 @@
+- Feature Name: microtvm_project_api
+- Start Date: 2020-06-09
+- RFC PR: [apache/tvm-rfc
gromero commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677788445
##
File path: python/tvm/micro/project.py
##
@@ -0,0 +1,97 @@
+"""Defines glue wrappers around the Project API which mate to TVM
interfaces."""
+
+from ..con
gromero commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677788445
##
File path: python/tvm/micro/project.py
##
@@ -0,0 +1,97 @@
+"""Defines glue wrappers around the Project API which mate to TVM
interfaces."""
+
+from ..con
gromero commented on a change in pull request #8380:
URL: https://github.com/apache/tvm/pull/8380#discussion_r677788445
##
File path: python/tvm/micro/project.py
##
@@ -0,0 +1,97 @@
+"""Defines glue wrappers around the Project API which mate to TVM
interfaces."""
+
+from ..con
comaniac commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887787785
> @comaniac the RFC in my mind is mainly a design-level description of some
aspect of TVM. Like e.g. PEP, they are meant to be consumed by people less
familiar with the TVM codeba
AndrewZhaoLuo commented on pull request #8517:
URL: https://github.com/apache/tvm/pull/8517#issuecomment-887776528
--
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.
To unsubs
kparzysz-quic commented on a change in pull request #8516:
URL: https://github.com/apache/tvm/pull/8516#discussion_r677730085
##
File path: src/tir/transforms/inject_copy_intrin.cc
##
@@ -157,19 +155,12 @@ class CopyIntrinInjector : public StmtMutator {
}
// Get storage s
areusch commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887764234
@comaniac the RFC in my mind is mainly a design-level description of some
aspect of TVM. Like e.g. PEP, they are meant to be consumed by people less
familiar with the TVM codebase
comaniac commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887750459
> i don't mind if we have a bunch of closed tracking issues. we can
categorize them. i agree with @u99127 that maintaining a record is important,
and i also think it makes sense t
areusch commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887736594
i don't mind if we have a bunch of closed tracking issues. we can categorize
them. i agree with @u99127 that maintaining a record is important, and i also
think it makes sense that
comaniac commented on pull request #8131:
URL: https://github.com/apache/tvm/pull/8131#issuecomment-887720375
Gentle ping @akmaru
--
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 co
This is an automated email from the ASF dual-hosted git repository.
mbrookhart pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
discard be5502e Merge jenkinsfile
discard 903c853 Add uses_gpu to onnx node tests
discard 03178c4 add onnx t
comaniac commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887701334
> Deleting an issue is not something we should do - keeping a record of why
something was rejected is useful on a later date to know why but perhaps the
issue of too many issues w
jroesch commented on pull request #8517:
URL: https://github.com/apache/tvm/pull/8517#issuecomment-887697690
> > As long as we don't implicitly downcast I think this should be fine, can
you test behavior of storing both an i32/u32 computation in i16/u16, and the
other way around?
>
u99127 commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887696764
> > I'd suggest that "nearly done" is ambiguous? As a less ambiguous
alternative I'd propose always opening a tracking issue (if the RFC is big
enough to require it) when you raise
jroesch commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887696449
LGTM thanks @comaniac
--
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.
comaniac pushed a change to branch comaniac-patch-1
in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git.
from 8d4be1a Update README.md
add 4cde53e Update README.md
No new revisions were added by this updat
comaniac commented on a change in pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#discussion_r677656411
##
File path: README.md
##
@@ -83,8 +83,10 @@ the RFC process:
- The formal RFC may link back to the original discussion if there is
additional
tqchen commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887690812
cc @apache/tvm-committers for awareness. Given this change seems to be
non-controversial, we can adopt lazy consensus and merge after 3 days if no
objection comes up
--
This is a
comaniac commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887690611
> I'd suggest that "nearly done" is ambiguous? As a less ambiguous
alternative I'd propose always opening a tracking issue (if the RFC is big
enough to require it) when you raise
junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r677650502
##
File path: rfcs/0001-meta-schedule-autotensorir.md
##
@@ -0,0 +1,604 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+* Feature Name: Meta Schedule (Formerly Aut
Mousius commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887686396
Hi @comaniac,
Thanks for suggesting this, it's been on my mind :smile_cat:
I'd suggest that "nearly done" is ambiguous? As a less ambiguous alternative
I'd propose al
Lunderberg commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677646517
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we avo
comaniac commented on a change in pull request #6:
URL: https://github.com/apache/tvm-rfcs/pull/6#discussion_r677642360
##
File path: rfcs/0001-AMP_pass.md
##
@@ -0,0 +1,137 @@
+- Feature Name: Automatic Mixed Precision Pass
+- Start Date: 2021-06-08
+- RFC PR: TODO
+- GitHub
comaniac commented on pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#issuecomment-887681011
cc @tqchen @hogepodge @areusch @jroesch
--
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.
comaniac pushed a change to branch comaniac-patch-1
in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git.
from 5e0e01c Update the guideline of RFC tracking issues
add 8d4be1a Update README.md
No new revisio
comaniac commented on a change in pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13#discussion_r677640791
##
File path: README.md
##
@@ -83,8 +83,9 @@ the RFC process:
- The formal RFC may link back to the original discussion if there is
additional c
comaniac opened a new pull request #13:
URL: https://github.com/apache/tvm-rfcs/pull/13
Based on the two RFCs I've reviewed, there are two points related to the RFC
tracking issue could be improved IMHO.
1. We currently state that the tracking issue should be opened after the RFC
PR
This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a change to branch comaniac-patch-1
in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git.
at 5e0e01c Update the guideline of RFC tracking issues
No new revisions were added by this update.
comaniac commented on a change in pull request #6:
URL: https://github.com/apache/tvm-rfcs/pull/6#discussion_r677616527
##
File path: rfcs/0001-AMP_pass.md
##
@@ -0,0 +1,137 @@
+- Feature Name: Automatic Mixed Precision Pass
+- Start Date: 2021-06-08
+- RFC PR: TODO
+- GitHub
tkonolige commented on a change in pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#discussion_r677625184
##
File path: python/tvm/topi/cuda/scatter.py
##
@@ -789,42 +790,78 @@ def gen_ir(data_ptr, indices_ptr, updates_ptr, out_ptr):
# For now we avoi
tkonolige commented on pull request #8479:
URL: https://github.com/apache/tvm/pull/8479#issuecomment-887657602
@CaptainDuke CI has been having issues. Just push a new commit and it will
re-run.
--
This is an automated message from the Apache Git Service.
To respond to the message, please
1 - 100 of 118 matches
Mail list logo