moderato opened a new pull request #5811:
URL: https://github.com/apache/incubator-tvm/pull/5811
Hello! This is my first time sending a pull-request. I found when the
`candidate` policy is chosen for `define_reorder`, AutoTVM throws an error of
`xxx not in list`. It's because in
h
yjiangling opened a new issue #5810:
URL: https://github.com/apache/incubator-tvm/issues/5810
Hi,
When I compile a tensorflow pb model with TVM, it gives the following
error message:
NotImplementedError: The following operators are not implemented:
{'GatherTree'}
Is i
FrozenGene commented on issue #5774:
URL: https://github.com/apache/incubator-tvm/issues/5774#issuecomment-643903889
This model has been changed rapidly. Previous `hand_landmark.tflite` model
is just FP32 model simply. Like this:
 {
trunc
zhiics commented on a change in pull request #5770:
URL: https://github.com/apache/incubator-tvm/pull/5770#discussion_r439757500
##
File path: src/target/source/source_module.cc
##
@@ -152,8 +153,92 @@ runtime::Module DeviceSourceModuleCreate(
return runtime::Module(n);
}
moderato opened a new issue #5809:
URL: https://github.com/apache/incubator-tvm/issues/5809
Hello! I find that non-square ConfigSpace might be critical to a project I'm
working on, while currently this is not supported. By `non-square` I mean the
scheduling of one axis has a constraint tha
tqchen merged pull request #5807:
URL: https://github.com/apache/incubator-tvm/pull/5807
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 g
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 7385118 [topi] fix strategy for sparse dense cuda (#5782)
add d0f9889 [CI] Move cpu-only frontend tests
comaniac commented on pull request #5791:
URL: https://github.com/apache/incubator-tvm/pull/5791#issuecomment-643887744
This might be off the topic. I think it's possible to use the pattern
language to replace all "combine parallel XX op" passes. Maybe we could create
an issue to check it.
vinx13 merged pull request #5782:
URL: https://github.com/apache/incubator-tvm/pull/5782
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 g
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 25c1734 Allow RPCWrappedFunc to rewrite runtime::String as
std::string (#5796)
add 7385118 [topi] fix s
tqchen commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r439890429
##
File path: include/tvm/node/container.h
##
@@ -43,51 +45,1184 @@ using runtime::Downcast;
using runtime::IterAdapter;
using runtime::make_object
KnowingNothing commented on issue #5798:
URL: https://github.com/apache/incubator-tvm/issues/5798#issuecomment-643851612
I see. Thanks for your response.
This is an automated message from the Apache Git Service.
To respond to
hypercubestart opened a new pull request #5808:
URL: https://github.com/apache/incubator-tvm/pull/5808
Lazy Gradient Initialization currently only worked on tensor types. This
adds functionality to potentially recursive ADTs, functions, and TupleTypes.
Also:
- added `Check` functi
junrushao1994 commented on issue #5798:
URL: https://github.com/apache/incubator-tvm/issues/5798#issuecomment-643843846
@KnowingNothing you can work around it by “ulimit -s SOME-LARGE-NUMBER” to
make stack size larger
This i
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 b3b2705 [topi] fix sparse dense schedule on cuda (#5803)
add 25c1734 Allow RPCWrappedFunc to rewrite ru
tqchen merged pull request #5796:
URL: https://github.com/apache/incubator-tvm/pull/5796
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 g
junrushao1994 commented on pull request #5806:
URL: https://github.com/apache/incubator-tvm/pull/5806#issuecomment-643832486
Nice work :-)
This is an automated message from the Apache Git Service.
To respond to the message, p
junrushao1994 commented on a change in pull request #5806:
URL: https://github.com/apache/incubator-tvm/pull/5806#discussion_r439874434
##
File path: include/tvm/runtime/container.h
##
@@ -1410,10 +1344,114 @@ inline String& String::operator=(std::string other) {
inline Stri
vinx13 commented on a change in pull request #5782:
URL: https://github.com/apache/incubator-tvm/pull/5782#discussion_r439874460
##
File path: python/tvm/relay/op/strategy/x86.py
##
@@ -294,11 +294,16 @@ def batch_matmul_strategy_cpu(attrs, inputs, out_type,
target):
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r439874267
##
File path: include/tvm/node/container.h
##
@@ -43,51 +45,1184 @@ using runtime::Downcast;
using runtime::IterAdapter;
using runtime::make
antinucleon commented on pull request #5782:
URL: https://github.com/apache/incubator-tvm/pull/5782#issuecomment-643831181
Updated
This is an automated message from the Apache Git Service.
To respond to the message, please lo
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r439873826
##
File path: include/tvm/node/container.h
##
@@ -23,17 +23,19 @@
#ifndef TVM_NODE_CONTAINER_H_
#define TVM_NODE_CONTAINER_H_
+#define TVM
vinx13 merged pull request #5803:
URL: https://github.com/apache/incubator-tvm/pull/5803
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 g
This is an automated email from the ASF dual-hosted git repository.
wuwei 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 b3b2705 [topi] fix sparse dense schedule
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r439870068
##
File path: include/tvm/node/container.h
##
@@ -43,51 +45,1184 @@ using runtime::Downcast;
using runtime::IterAdapter;
using runtime::make
tqchen closed issue #5804:
URL: https://github.com/apache/incubator-tvm/issues/5804
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
tqchen commented on issue #5804:
URL: https://github.com/apache/incubator-tvm/issues/5804#issuecomment-643825044
Move discussion to https://discuss.tvm.ai/t/dump-module-to-llvm-ir/6966/8
This is an automated message from the
junrushao1994 commented on a change in pull request #5740:
URL: https://github.com/apache/incubator-tvm/pull/5740#discussion_r439869533
##
File path: include/tvm/runtime/container.h
##
@@ -1554,6 +1604,925 @@ struct PackedFuncValueConverter> {
}
};
+/*! \brief map node co
tqchen commented on issue #5774:
URL: https://github.com/apache/incubator-tvm/issues/5774#issuecomment-643814554
cc @FrozenGene
This is an automated message from the Apache Git Service.
To respond to the message, please log
dprankratz commented on pull request #5666:
URL: https://github.com/apache/incubator-tvm/pull/5666#issuecomment-643808103
@tqchen I did some more digging into using let nodes. Consider the following
expression:
```
floormod(floormod(a,b),floormod(c,d))
```
`floormod(a,b)` become
zhiics commented on a change in pull request #5807:
URL: https://github.com/apache/incubator-tvm/pull/5807#discussion_r439852151
##
File path: tests/scripts/task_python_frontend_cpu.sh
##
@@ -0,0 +1,37 @@
+#!/bin/bash
+# Licensed to the Apache Software Foundation (ASF) under on
tqchen commented on pull request #5807:
URL: https://github.com/apache/incubator-tvm/pull/5807#issuecomment-643798013
cc @yzhliu @zhiics @ZihengJiang
This is an automated message from the Apache Git Service.
To respond to th
tqchen merged pull request #5801:
URL: https://github.com/apache/incubator-tvm/pull/5801
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 g
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 4404748 [TIR][REFACTOR] Add tir prefix to type keys (#5802)
add 33f2fb6 [QUANTIZE] Add config switch fo
tqchen opened a new pull request #5807:
URL: https://github.com/apache/incubator-tvm/pull/5807
With the goal to reduce the overall CI time cost
This is an automated message from the Apache Git Service.
To respond to the messa
tqchen commented on issue #5318:
URL: https://github.com/apache/incubator-tvm/issues/5318#issuecomment-643795847
NOTE: The notnull support for composite types has a bit more complications,
we will stop working on it for now and then revisit once w ehave a solution.
--
tqchen commented on a change in pull request #5788:
URL: https://github.com/apache/incubator-tvm/pull/5788#discussion_r439850074
##
File path: src/arith/rewrite_simplify.cc
##
@@ -123,7 +123,7 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const AddNode*
op) {
// Pattern v
tqchen commented on a change in pull request #5788:
URL: https://github.com/apache/incubator-tvm/pull/5788#discussion_r439850074
##
File path: src/arith/rewrite_simplify.cc
##
@@ -123,7 +123,7 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const AddNode*
op) {
// Pattern v
sergei-grechanik commented on a change in pull request #5618:
URL: https://github.com/apache/incubator-tvm/pull/5618#discussion_r436795027
##
File path: include/tvm/arith/int_solver.h
##
@@ -26,17 +26,99 @@
#include
#include
+#include
#include
+#include
#include
ANSHUMAN87 commented on a change in pull request #5788:
URL: https://github.com/apache/incubator-tvm/pull/5788#discussion_r439848026
##
File path: src/arith/rewrite_simplify.cc
##
@@ -123,7 +123,7 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const AddNode*
op) {
// Patte
zhiics merged pull request #5802:
URL: https://github.com/apache/incubator-tvm/pull/5802
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 g
This is an automated email from the ASF dual-hosted git repository.
zhic 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 4404748 [TIR][REFACTOR] Add tir prefix to
zhiics opened a new pull request #5806:
URL: https://github.com/apache/incubator-tvm/pull/5806
Per #5792
@tqchen @junrushao1994
This is an automated message from the Apache Git Service.
To respond to the message,
cbalint13 opened a new pull request #5805:
URL: https://github.com/apache/incubator-tvm/pull/5805
This PR adds ```nn.batch_flatten``` as quantizable layer.
**Description**
* ```nn/batch_flatten``` is commonly used before ```nn.dense``` in final
layers.
* Proposed PR allows it t
45 matches
Mail list logo
