This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 08d7345 fix Relay build docstring (#7963)
08d7345 is
comaniac commented on pull request #7963:
URL: https://github.com/apache/tvm/pull/7963#issuecomment-830746435
Thanks @hypercubestart
--
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
comaniac merged pull request #7963:
URL: https://github.com/apache/tvm/pull/7963
--
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.
For queries about this service, please co
ZihengJiang merged pull request #7945:
URL: https://github.com/apache/tvm/pull/7945
--
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.
For queries about this service, please
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from ce8f52b Fix a memory leak in SetParams (#7960)
add b2c4f1c [RELAY] Turn reshape into nop in graph executor backend.
gromero commented on pull request #7914:
URL: https://github.com/apache/tvm/pull/7914#issuecomment-830716418
@areusch @mehrdadh Finally CI is happy :) Could I get reviews for that
change please? fyi @tom-gall @leandron @u99127
--
This is an automated message from the Apache Git Service
hypercubestart opened a new pull request #7963:
URL: https://github.com/apache/tvm/pull/7963
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 code reviews
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 1ec8660 [Topi] Fix arm_cpu bitserial schedule with elemwise ops.
(#7929)
add ce8f52b Fix a memory leak in SetParam
tqchen merged pull request #7960:
URL: https://github.com/apache/tvm/pull/7960
--
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.
For queries about this service, please cont
tqchen commented on pull request #7960:
URL: https://github.com/apache/tvm/pull/7960#issuecomment-830706549
Thanks @echuraev !
--
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 commen
masahi commented on pull request #7958:
URL: https://github.com/apache/tvm/pull/7958#issuecomment-830704967
Thanks, can we close https://github.com/apache/tvm/pull/7912?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
tqchen commented on pull request #7948:
URL: https://github.com/apache/tvm/pull/7948#issuecomment-830697859
THanks @jcf94 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 to go 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/tvm.git.
from 63e9e5a [RPC] Bugfix. Removed server forcing IPv4 protocol (#7953)
add 1ec8660 [Topi] Fix arm_cpu bitserial schedul
tqchen merged pull request #7929:
URL: https://github.com/apache/tvm/pull/7929
--
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.
For queries about this service, please cont
tqchen closed issue #7909:
URL: https://github.com/apache/tvm/issues/7909
--
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.
For queries about this service, please contact I
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 6d555b6 Correctly build with -runtime=c without -system-lib (#7954)
add 63e9e5a [RPC] Bugfix. Removed server forcin
tqchen merged pull request #7953:
URL: https://github.com/apache/tvm/pull/7953
--
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.
For queries about this service, please cont
tqchen edited a comment on pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#issuecomment-830676898
@areusch I pushed an alternative implementation that can preserve the python
exception types. I started with this one but then decided to go with the
approach because most e
tqchen commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624549140
##
File path: include/tvm/runtime/c_backend_api.h
##
@@ -99,6 +100,19 @@ TVM_DLL void* TVMBackendAllocWorkspace(int device_type, int
device_id, uint64_t
*/
tqchen commented on pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#issuecomment-830676898
@areusch I pushed an alternative implementation that can preserve the python
exception types. I started with this one but then decided to go with the
approach because most exceptio
mehrdadh commented on pull request #7903:
URL: https://github.com/apache/tvm/pull/7903#issuecomment-830669619
@areusch this PR finally passed CI. PTAL.
Thansk!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
UR
areusch commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624542412
##
File path: include/tvm/runtime/registry.h
##
@@ -52,6 +52,45 @@
namespace tvm {
namespace runtime {
+/*!
+ * \brief Check if signals have been sent to
areusch commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624542412
##
File path: include/tvm/runtime/registry.h
##
@@ -52,6 +52,45 @@
namespace tvm {
namespace runtime {
+/*!
+ * \brief Check if signals have been sent to
tqchen commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624536898
##
File path: include/tvm/runtime/registry.h
##
@@ -52,6 +52,45 @@
namespace tvm {
namespace runtime {
+/*!
+ * \brief Check if signals have been sent to t
areusch commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624530604
##
File path: include/tvm/runtime/registry.h
##
@@ -52,6 +52,45 @@
namespace tvm {
namespace runtime {
+/*!
+ * \brief Check if signals have been sent to
areusch commented on a change in pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#discussion_r624529424
##
File path: src/runtime/registry.cc
##
@@ -102,6 +103,89 @@ std::vector Registry::ListNames() {
return keys;
}
+/*!
+ * \brief Execution environment s
areusch commented on pull request #7250:
URL: https://github.com/apache/tvm/pull/7250#issuecomment-830653952
hey @Tantalus13A98B5F, just to make sure I understand: in the case you're
running autotuning with a sparse-dense matrix, you may want to supply fixed
indices rather than use random
areusch commented on pull request #7939:
URL: https://github.com/apache/tvm/pull/7939#issuecomment-830651571
@tkonolige i see, so the problem is that gen_weights was False here?
basically my only concern is whether we need to make a more fundamental change
to params to fix common use case,
Hzfengsy opened a new pull request #7962:
URL: https://github.com/apache/tvm/pull/7962
In this PR, we add the last lowering pass for TensorIR FlattenBuffer, which
converts high-dimensional buffer access (BufferLoad/BufferStore) into low-level
access (Load/Store).
Also a minor fix of
echuraev edited a comment on pull request #7960:
URL: https://github.com/apache/tvm/pull/7960#issuecomment-830619896
> Thanks @echuraev can you also search the usage of ToDLPack() and update
other locations? Likely they will also cause memleak
Done. Found all other usages of `ToDLPac
tqchen opened a new pull request #7961:
URL: https://github.com/apache/tvm/pull/7961
This PR uses the PopenWorker to handle the tracker start up
and makes the tracker jupyter friendly.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on
echuraev commented on pull request #7960:
URL: https://github.com/apache/tvm/pull/7960#issuecomment-830619896
> Thanks @echuraev can you also search the usage of ToDLPack() and update
other locations? Likely they will also cause memleak
Done. Find all other usages of `ToDLPack()` and
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 6d555b6 Correctly build with -runtime=c without -syste
tqchen commented on pull request #7954:
URL: https://github.com/apache/tvm/pull/7954#issuecomment-830619251
Thanks @cgerum !
--
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.
tqchen merged pull request #7954:
URL: https://github.com/apache/tvm/pull/7954
--
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.
For queries about this service, please cont
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 1c5684c [microTVM] Increase host memory size (#7933)
1
tqchen merged pull request #7933:
URL: https://github.com/apache/tvm/pull/7933
--
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.
For queries about this service, please cont
tqchen commented on pull request #7960:
URL: https://github.com/apache/tvm/pull/7960#issuecomment-830617945
Thanks @echuraev can you also search the usage of ToDLPack() and update
other locations? Likely they will also cause memleak
--
This is an automated message from the Apache Git Ser
tqchen commented on pull request #7834:
URL: https://github.com/apache/tvm/pull/7834#issuecomment-830617843
Thanks @csullivan This is merged
--
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 s
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 2215d73 [OpenCL] Refactor cl_program generation (#7834
tqchen merged pull request #7834:
URL: https://github.com/apache/tvm/pull/7834
--
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.
For queries about this service, please cont
tqchen commented on pull request #7785:
URL: https://github.com/apache/tvm/pull/7785#issuecomment-830617762
Added one more comment. I dismissed my original requests as they are
fulfilled. Didn't take a chance to do a full read, but will leave to @areusch
to manage the PR
--
This is an a
tqchen commented on a change in pull request #7785:
URL: https://github.com/apache/tvm/pull/7785#discussion_r624496567
##
File path: src/relay/backend/aot_executor_codegen.cc
##
@@ -0,0 +1,672 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more con
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 3d380fc [Target][Legalization]Add Tir Level Legalizati
tqchen merged pull request #7936:
URL: https://github.com/apache/tvm/pull/7936
--
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.
For queries about this service, please cont
echuraev opened a new pull request #7960:
URL: https://github.com/apache/tvm/pull/7960
ToDLPack creates a DLManagedTensor instance, but nobody delete this i8n
proper way. We can use operator-> for getting access to DLTensor.
Thanks for contributing to TVM! Please refer to guideli
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new dc1f189 [AutoTVM] [TOPI] Support AutoTVM for int4 tens
ZihengJiang merged pull request #7831:
URL: https://github.com/apache/tvm/pull/7831
--
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.
For queries about this service, please
48 matches
Mail list logo
