liangfu commented on pull request #6914:
URL: https://github.com/apache/incubator-tvm/pull/6914#issuecomment-726638196
cc @junrushao1994
This is an automated message from the Apache Git Service.
To respond to the message,
merrymercy commented on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-726736491
@mbaret The tutorial is online now. You can try it
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/incubator-tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 57d59b7 update index.html
merrymercy edited a comment on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-726736491
@mbaret The tutorial is online now
https://tvm.apache.org/docs/tutorials/auto_scheduler/tune_network_cuda.html
You can try it and any feedback is welcomed!
merrymercy merged pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882
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
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from f952fa7 [TFLite runtime] Allow to set number of threads to TFLite
interpreter (#6901)
add 050a836
merrymercy edited a comment on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-726608309
Let me merge this PR first because it fixed multiple bugs.
I will send follow up PRs to improve the fallback mechanism when no valid
schedule is found.
merrymercy commented on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-726608309
Let me merge this first as it fixed multiple bugs.
I will send follow up PRs to improve the fallback mechanism when no valid
schedule is found.
liangfu opened a new pull request #6914:
URL: https://github.com/apache/incubator-tvm/pull/6914
This PR improves the runtime::Array in #5585 by adding support to append new
item in Python side, and push_back a new item in C++.
merrymercy edited a comment on pull request #6882:
URL: https://github.com/apache/incubator-tvm/pull/6882#issuecomment-726608309
Let me merge this PR first because it fixed multiple bugs.
I will send follow up PRs to improve the fallback mechanism in `relay.build`
when there is no valid
rohanmukh commented on a change in pull request #6905:
URL: https://github.com/apache/incubator-tvm/pull/6905#discussion_r523166626
##
File path: tests/python/contrib/test_tensorrt.py
##
@@ -874,44 +972,7 @@ def test_densenet121():
run_and_verify_model("densenet121")
areusch commented on pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915#issuecomment-726994238
missed one thing, making draft.
This is an automated message from the Apache Git Service.
To respond to
areusch commented on pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915#issuecomment-727071435
@tqchen i was originally planning to do that but the implementation is
already in this file under operator<<.
trevor-m commented on a change in pull request #6905:
URL: https://github.com/apache/incubator-tvm/pull/6905#discussion_r523133866
##
File path: tests/python/contrib/test_tensorrt.py
##
@@ -874,44 +972,7 @@ def test_densenet121():
run_and_verify_model("densenet121")
zhiics commented on a change in pull request #6905:
URL: https://github.com/apache/incubator-tvm/pull/6905#discussion_r523123910
##
File path: python/tvm/relay/op/contrib/tensorrt.py
##
@@ -152,13 +153,50 @@ def partition_for_tensorrt(
with
tqchen commented on pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915#issuecomment-727074424
OK, let us go with this then
This is an automated message from the Apache Git Service.
To respond to the
areusch commented on pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915#issuecomment-726993170
@tqchen
This is an automated message from the Apache Git Service.
To respond to the message, please log
areusch opened a new pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915
Small cleanup PR to move logic around building and examining RPC contexts
into a single place. Helpful when building the pre-linked parameter PR (coming
soon).
areusch opened a new pull request #6916:
URL: https://github.com/apache/incubator-tvm/pull/6916
When debugging vmalloc() on ARM devices, %zu was printing as "zu." This
change fixes that.
* Some platforms need to use an alternate printf() to support basic
things like %zu.
areusch opened a new pull request #6917:
URL: https://github.com/apache/incubator-tvm/pull/6917
RFC pending.
This PR implements changes to support generating Modules that contain
parameters pre-linked. For CPU contexts, these modules don't require any
copying before launching
tqchen commented on pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915#issuecomment-727045043
It would be helpful to keep these as an internal header for now, because the
implementation of RPC should be hidden from the user.
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/incubator-tvm.git.
from b4f99e5 [TRT][BYOC] handling dynamism in TensorRT to support OD
models (#6905)
add 55d8172 Consolidate
icemelon9 commented on a change in pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#discussion_r523313472
##
File path: python/tvm/topi/cuda/dense.py
##
@@ -77,8 +77,8 @@ def _callback(op):
def _schedule_dense_small_batch(cfg, s, C):
-A, _ =
icemelon9 commented on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-727106573
I have a question. What do you mean "input's shape's second dim is unknown"?
TVM is able to compile the kernel even though the dim is a sym var.
lixiaoquan closed issue #6913:
URL: https://github.com/apache/incubator-tvm/issues/6913
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
lixiaoquan commented on issue #6913:
URL: https://github.com/apache/incubator-tvm/issues/6913#issuecomment-727101245
Thanks all, it is solved.
This is an automated message from the Apache Git Service.
To respond to the
icemelon9 commented on a change in pull request #6912:
URL: https://github.com/apache/incubator-tvm/pull/6912#discussion_r523310191
##
File path: src/relay/backend/compile_engine.cc
##
@@ -420,38 +420,59 @@ class MakeShapeFunc : public
backend::MemoizedExprTranslator>
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7c39a4 Fix edge cases in const_int_bound and fold_scale_axis (#6911)
add b4f99e5 [TRT][BYOC]
anijain2305 opened a new pull request #6918:
URL: https://github.com/apache/incubator-tvm/pull/6918
As title
@zhiics
This is an automated message from the Apache Git Service.
To respond to the message, please log on
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7c39a4 Fix edge cases in const_int_bound and fold_scale_axis (#6911)
add b4f99e5 [TRT][BYOC]
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7c39a4 Fix edge cases in const_int_bound and fold_scale_axis (#6911)
add b4f99e5 [TRT][BYOC]
areusch commented on pull request #6916:
URL: https://github.com/apache/incubator-tvm/pull/6916#issuecomment-727117673
@tqchen @u99127 @tom-gall @manupa-arm
This is an automated message from the Apache Git Service.
To
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7c39a4 Fix edge cases in const_int_bound and fold_scale_axis (#6911)
add b4f99e5 [TRT][BYOC]
wweic commented on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-727102464
lgtm. pls fix the test failure. cc @icemelon9 @kevinthesun
This is an automated message from the Apache
anijain2305 commented on pull request #6905:
URL: https://github.com/apache/incubator-tvm/pull/6905#issuecomment-727084182
Thanks @rohanmukh @zhiics @trevor-m This is merged
This is an automated message from the Apache Git
anijain2305 merged pull request #6905:
URL: https://github.com/apache/incubator-tvm/pull/6905
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7c39a4 Fix edge cases in const_int_bound and fold_scale_axis (#6911)
add b4f99e5 [TRT][BYOC]
tqchen merged pull request #6915:
URL: https://github.com/apache/incubator-tvm/pull/6915
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 pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#issuecomment-726801407
> Just to check, you're only transposing the dense matrix? Also, what is the
density of the sparse matrix?
>
> I'm curious, could you do a benchmark with a
tqchen commented on issue #6913:
URL: https://github.com/apache/incubator-tvm/issues/6913#issuecomment-726771483
Please check if #6911 resolves the issue
This is an automated message from the Apache Git Service.
To respond
tqchen merged pull request #6911:
URL: https://github.com/apache/incubator-tvm/pull/6911
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 main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 050a836 [AutoScheduler] Tutorial on auto-scheduling a network for GPU
(#6882)
add c7c39a4 Fix edge
tqchen commented on pull request #6914:
URL: https://github.com/apache/incubator-tvm/pull/6914#issuecomment-726770963
Our current inherant assumption for Array and other data structures so far
is that they are immutable, and applies copy on write on the c++ side. Because
there is not a
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/incubator-tvm.git.
from 050a836 [AutoScheduler] Tutorial on auto-scheduling a network for GPU
(#6882)
add c7c39a4 Fix edge
ANSHUMAN87 edited a comment on pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#issuecomment-726801407
> Just to check, you're only transposing the dense matrix? Also, what is the
density of the sparse matrix?
>
> I'm curious, could you do a benchmark with
45 matches
Mail list logo
