This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 639358e [relay][topi] Add operation relay.nn.dilate() which calls
topi.nn.dilate() (#5331)
add 16d0d56
SXM-inspur opened a new pull request #5450:
URL: https://github.com/apache/incubator-tvm/pull/5450
The runtime of global_ave_pool took about 14.8% in Resnet50_v2 with
batchsize of 32, when Tensor Core is enabled on Tesla T4 GPU. The runtime
decreased to 0.134%, after optimizations in
maheshambule commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r415688419
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1770,6 +1775,12 @@ def convert_pool2d(self, op, pool_type):
assert
n-nez commented on pull request #5451:
URL: https://github.com/apache/incubator-tvm/pull/5451#issuecomment-619808194
cc @masahi
This is an automated message from the Apache Git Service.
To respond to the message, please log
n-nez opened a new pull request #5451:
URL: https://github.com/apache/incubator-tvm/pull/5451
Symptoms
```
Traceback (most recent call last):
File "test_forward.py", line 1646, in
test_forward_transpose()
File "test_forward.py", line 755, in test_forward_transpose
maheshambule opened a new pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452
Adds support for L2_POOL_2D operator in TFLITE frontened.
Ref:
https://www.tensorflow.org/lite/guide/ops_compatibility
This is an automated email from the ASF dual-hosted git repository.
kazum pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from a60de36 [ONNX]GatherNd, Round, IsNaN, IsInf (#5445)
add 639358e [relay][topi] Add operation
kazum commented on pull request #5331:
URL: https://github.com/apache/incubator-tvm/pull/5331#issuecomment-619792700
Thanks @notoraptor @siju-samuel !
This is an automated message from the Apache Git Service.
To respond to
FrozenGene commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r415679526
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1770,6 +1775,12 @@ def convert_pool2d(self, op, pool_type):
assert
masahi commented on pull request #5451:
URL: https://github.com/apache/incubator-tvm/pull/5451#issuecomment-619925257
Thanks @n-nez
This is an automated message from the Apache Git Service.
To respond to the message, please
maheshambule commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r415749383
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -487,6 +487,31 @@ def test_forward_pooling():
u99127 commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r415699554
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -487,6 +487,31 @@ def test_forward_pooling():
strides=[2,
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 16d0d56 [Pytorch] fix translation of transpose when axis argument is
as a list (#5451)
add 17cd27d
mbaret commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620051291
I don't think we'd need to treat constant nodes differently everywhere else.
At least, in the previous version of AnnotatedRegionSet using the recursive
pattern, the
siju-samuel opened a new pull request #5453:
URL: https://github.com/apache/incubator-tvm/pull/5453
`ReduceLogSumExp` op support added in Relay and ONNX Frontend.
@masahi @FrozenGene Could you please help me to review this PR. Thanks
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415981441
##
File path: src/runtime/micro/host_driven/utvm_runtime.c
##
@@ -34,89 +34,148 @@ extern "C" {
#include "utvm_runtime.h"
-// Task pointers
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415980487
##
File path: src/runtime/micro/host_driven/utvm_device_dylib_redirect.c
##
@@ -32,10 +32,10 @@ extern "C" {
#include
#include
-void
kevinthesun commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r416046045
##
File path: src/relay/op/tensor/transform.cc
##
@@ -650,13 +670,59 @@ Array ReshapeCompute(const Attrs& attrs,
return {
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415970450
##
File path: python/tvm/target/arm_isa.py
##
@@ -0,0 +1,34 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415990923
##
File path: src/target/source/codegen_c_host.cc
##
@@ -20,10 +20,10 @@
/*!
* \file codegen_c_host.cc
*/
-#include
+#include
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415942734
##
File path: Makefile
##
@@ -73,7 +73,10 @@ build/libtvm_web_runtime.js: build/libtvm_web_runtime.bc
cpplint:
python3
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415959267
##
File path: python/tvm/micro/device/host.py
##
@@ -17,12 +17,26 @@
"""Compilation and config definitions for the host emulated device"""
import
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415958560
##
File path: python/tvm/micro/device/base.py
##
@@ -92,71 +95,142 @@ def create_micro_lib_base(
options : List[str]
additional
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415958851
##
File path: python/tvm/micro/device/base.py
##
@@ -92,71 +95,142 @@ def create_micro_lib_base(
options : List[str]
additional
wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416007695
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] = {'x',
maheshambule commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r416041366
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1770,6 +1775,12 @@ def convert_pool2d(self, op, pool_type):
assert
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415947706
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -36,23 +55,41 @@ def create_micro_lib(obj_path, src_path, lib_type,
options=None):
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415961064
##
File path: python/tvm/relay/_parser.py
##
@@ -340,7 +342,10 @@ def visitLocalVar(self, ctx):
return local_var
def
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415967381
##
File path: python/tvm/relay/op/strategy/arm_cpu.py
##
@@ -267,7 +281,7 @@ def bitserial_conv2d_strategy_arm_cpu(attrs, inputs,
out_type,
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415991766
##
File path: topi/python/topi/arm_cpu/cortex_m7/conv2d/direct.py
##
@@ -0,0 +1,177 @@
+# Licensed to the Apache Software Foundation (ASF) under
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415983620
##
File path: src/runtime/micro/host_driven/utvm_runtime.c
##
@@ -34,89 +34,148 @@ extern "C" {
#include "utvm_runtime.h"
-// Task pointers
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415984080
##
File path: src/runtime/micro/host_driven/utvm_runtime.c
##
@@ -34,89 +34,148 @@ extern "C" {
#include "utvm_runtime.h"
-// Task pointers
siju-samuel commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r415997917
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -2075,6 +2077,29 @@ def convert_space_to_depth(self, op):
return out
+
wpan11nv commented on pull request #5382:
URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-620140371
> Do you mean requiring the users to tag the iter_var or we do it in
InferBound? If the former, maybe we can merge this PR first and then start an
RFC for the API
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415949272
##
File path: python/tvm/autotvm/tuner/tuner.py
##
@@ -150,7 +150,15 @@ def tune(self, n_trial, measure_option,
early_stopping=None, callbacks=(),
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415981837
##
File path: src/runtime/micro/host_driven/utvm_runtime.c
##
@@ -34,89 +34,148 @@ extern "C" {
#include "utvm_runtime.h"
-// Task pointers
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415989331
##
File path: src/runtime/micro/micro_common.h
##
@@ -52,28 +53,115 @@ enum class SectionKind : size_t {
kNumKinds,
};
-/*! \brief union for
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415988618
##
File path: src/runtime/micro/micro_common.h
##
@@ -52,28 +53,115 @@ enum class SectionKind : size_t {
kNumKinds,
};
-/*! \brief union for
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r415988262
##
File path: src/runtime/micro/host_driven/utvm_runtime.h
##
@@ -46,20 +62,38 @@ typedef struct {
int32_t num_args;
} UTVMTask;
+/*!
+ *
siju-samuel commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r415987001
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -561,6 +561,31 @@ def test_forward_pooling():
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416116610
##
File path: python/tvm/autotvm/tuner/tuner.py
##
@@ -150,7 +150,15 @@ def tune(self, n_trial, measure_option,
early_stopping=None,
u99127 commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416152206
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -2075,6 +2077,29 @@ def convert_space_to_depth(self, op):
return out
+def
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416120588
##
File path: src/runtime/micro/micro_session.cc
##
@@ -209,59 +246,124 @@ MicroSession::~MicroSession() {
low_level_device_ = nullptr;
}
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416121088
##
File path: src/runtime/micro/micro_session.cc
##
@@ -404,39 +509,74 @@ DevPtr
MicroSession::EncoderAppend(TargetDataLayoutEncoder* encoder,
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416121933
##
File path: tests/python/unittest/test_runtime_micro.py
##
@@ -25,8 +25,25 @@
from tvm.micro import create_micro_mod
from tvm.relay.testing
tqchen commented on issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455#issuecomment-620223340
also cc @yongfeng-nv @hzfan since both of you have touched/reviewed the
const int bound recently
This is an
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416140211
##
File path: python/tvm/autotvm/tuner/callback.py
##
@@ -144,12 +144,12 @@ def __del__(self):
def _callback(tuner, inputs, results):
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416140782
##
File path: python/tvm/autotvm/tuner/tuner.py
##
@@ -150,7 +150,15 @@ def tune(self, n_trial, measure_option,
early_stopping=None, callbacks=(),
mbrookhart opened a new pull request #5454:
URL: https://github.com/apache/incubator-tvm/pull/5454
@jwfromm @masahi @soiferj
Thank you!
This is an automated message from the Apache Git Service.
To respond to the
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416122541
##
File path: topi/python/topi/arm_cpu/cortex_m7/micro_kernel/gemm.py
##
@@ -0,0 +1,221 @@
+# Licensed to the Apache Software Foundation (ASF)
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416122882
##
File path: python/tvm/autotvm/tuner/callback.py
##
@@ -144,12 +144,12 @@ def __del__(self):
def _callback(tuner, inputs, results):
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416122964
##
File path: python/tvm/autotvm/tuner/callback.py
##
@@ -144,12 +144,12 @@ def __del__(self):
def _callback(tuner, inputs, results):
tqchen commented on issue #5449:
URL: https://github.com/apache/incubator-tvm/issues/5449#issuecomment-620220730
Please open a new trouble shooting thread on https://discuss.tvm.ai/
This is an automated message from the
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416138054
##
File path: src/runtime/micro/micro_session.cc
##
@@ -209,59 +246,124 @@ MicroSession::~MicroSession() {
low_level_device_ = nullptr;
}
u99127 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r413829506
##
File path: python/tvm/autotvm/measure/local_executor.py
##
@@ -145,6 +145,7 @@ def submit(self, func, *args, **kwargs):
if not
tqchen commented on issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455#issuecomment-620223143
```
self =
args = (IRModuleNode( {GlobalVar(main): FunctionNode([Var(x,
ty=TensorType([1, 1, 64, 64], uint8))], TensorType([1, 16, 64, 6...Type([1, 1,
64, 64], uint8),
tqchen opened a new issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455
In the past week I attempted to upgrade the docker image CPU to
bionic(ubuntu 18.04), during the time, a new unittest error occurs(note that
the master CI was fine) in the int8 intrinsic test,
tqchen commented on issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455#issuecomment-620222412
cc @anijain2305
This is an automated message from the Apache Git Service.
To respond to the message, please
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416138909
##
File path: tests/python/unittest/test_runtime_micro.py
##
@@ -25,8 +25,25 @@
from tvm.micro import create_micro_mod
from tvm.relay.testing
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416139282
##
File path: topi/python/topi/arm_cpu/cortex_m7/micro_kernel/gemm.py
##
@@ -0,0 +1,221 @@
+# Licensed to the Apache Software Foundation (ASF)
u99127 commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r416144493
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -487,6 +487,31 @@ def test_forward_pooling():
strides=[2,
masahi commented on issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455#issuecomment-620230784
I also saw this error when running `test_op_level2.py` locally. It happens
randomly.
This is an automated
tqchen commented on issue #5448:
URL: https://github.com/apache/incubator-tvm/issues/5448#issuecomment-620221216
It is likely that you will also need to update your cython module, by typing
`make cython3`, for future questions, please open a new trouble shooting thread
on
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416140904
##
File path: src/runtime/micro/micro_session.cc
##
@@ -209,59 +246,124 @@ MicroSession::~MicroSession() {
low_level_device_ = nullptr;
}
u99127 commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r416146885
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1770,6 +1775,12 @@ def convert_pool2d(self, op, pool_type):
assert
kevinthesun commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r416207982
##
File path: src/relay/transforms/pattern_util.h
##
@@ -554,7 +554,10 @@ static inline Expr Reshape(Expr data, Array
newshape) {
zhiics opened a new pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457
The problem is described here:
https://discuss.tvm.ai/t/relay-pass-feature-check-fail-during-fold-constant-pass/6498
@MarisaKirisame Can you take a look and see if the change makes sense?
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r416214792
##
File path: python/tvm/relay/op/transform.py
##
@@ -613,13 +613,13 @@ def strided_slice(data, begin, end, strides=None):
data :
kevinthesun commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r416228918
##
File path: src/relay/transforms/pattern_util.h
##
@@ -554,7 +554,10 @@ static inline Expr Reshape(Expr data, Array
newshape) {
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416249062
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
liangfu commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416266168
##
File path: src/target/source/codegen_c_host.cc
##
@@ -20,10 +20,10 @@
/*!
* \file codegen_c_host.cc
*/
-#include
+#include
liangfu commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416272213
##
File path: Makefile
##
@@ -73,7 +73,10 @@ build/libtvm_web_runtime.js: build/libtvm_web_runtime.bc
cpplint:
python3
wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416240568
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] = {'x',
wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416251080
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] = {'x',
masahi commented on pull request #5454:
URL: https://github.com/apache/incubator-tvm/pull/5454#issuecomment-620320682
Thanks @mbrookhart
This is an automated message from the Apache Git Service.
To respond to the message,
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 17cd27d [TFLite Runtime] Add TFLite Runtime dependencies to CI CPU
docker build (#5437)
add 702db6f
tmoreau89 commented on pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#issuecomment-620258389
@u99127 the pieces that changed the behavior of autoTVM are a small fraction
of the overall PR; so post-changes, the PR will remain significantly large /
unchanged.
kevinthesun commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r416201926
##
File path: src/relay/op/tensor/transform.cc
##
@@ -650,13 +670,59 @@ Array ReshapeCompute(const Attrs& attrs,
return {
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416253058
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
s1113950 opened a new pull request #5456:
URL: https://github.com/apache/incubator-tvm/pull/5456
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
tmoreau89 commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416178024
##
File path: python/tvm/autotvm/measure/local_executor.py
##
@@ -145,6 +145,7 @@ def submit(self, func, *args, **kwargs):
if not
wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416246643
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] = {'x',
tqchen opened a new issue #5458:
URL: https://github.com/apache/incubator-tvm/issues/5458
This is an error message generated by the mxnet-mkl image in the current
master. The error was due to the operator `amp_multicast` is not implmented in
the mxnet frontend(likely due to a mkl
tqchen commented on issue #5458:
URL: https://github.com/apache/incubator-tvm/issues/5458#issuecomment-620312769
cc @icemelon9 @shoubhik @anijain2305
This is an automated message from the Apache Git Service.
To respond to
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416238967
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416245487
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
boh-inspur commented on pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#issuecomment-620311830
>
>
> Do you see any issue to implement in a consistent way?
>
> uint_8x2 could be also stored as uint16_t, the same as uint8_t. If I am
not mistaken,
liangfu commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416273515
##
File path: python/tvm/exec/rpc_server.py
##
@@ -100,27 +101,34 @@ def server_shutdown():
parser.add_argument('--port-end', type=int,
liangfu commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416273092
##
File path: python/tvm/micro/device/arm/stm32f746xx.py
##
@@ -36,23 +55,41 @@ def create_micro_lib(obj_path, src_path, lib_type,
options=None):
yongfeng-nv commented on issue #5455:
URL: https://github.com/apache/incubator-tvm/issues/5455#issuecomment-620373532
Ran the test in tvmai/ci-cpu:v0.62-t0, but couldn't reproduce the failure.
I cloned and built TVM by myself, as I I didn't find TVM in the docker image.
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch tmoreau89-patch-1
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
at 57e5c13 [COMMUNITY] @liangfu -> committer
This branch includes the following new commits:
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a commit to branch tmoreau89-patch-1
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
commit 57e5c131992ee59a03d6ce11c97f65437d27dea6
Author: Thierry Moreau
AuthorDate: Mon Apr 27 22:31:34 2020
tmoreau89 opened a new pull request #5460:
URL: https://github.com/apache/incubator-tvm/pull/5460
Please join us to welcome @liangfu as a committer. He has helped maintain
much of the Chisel codebase for VTA and notably has brought support to Intel
FPGAs. More recently he contributed by
kevinthesun opened a new pull request #5459:
URL: https://github.com/apache/incubator-tvm/pull/5459
Support symbolic k for TopK.
Support symbolic shape for Ones, Zeros and Full.
@icemelon9 @yongwww @lixiaoquan
yzhliu commented on a change in pull request #5357:
URL: https://github.com/apache/incubator-tvm/pull/5357#discussion_r416315915
##
File path: src/relay/transforms/fold_scale_axis.cc
##
@@ -39,6 +39,10 @@ namespace relay {
*
* Use namespace to reduce potential naming
murdockhou opened a new issue #5448:
URL: https://github.com/apache/incubator-tvm/issues/5448
I have update the tvm to the latest(2020/04/27). After this, I run the code
that convert pyorch model to tvm. But get error in the first like this:
```
Traceback (most recent call last):
lixiaoquan commented on a change in pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#discussion_r415554589
##
File path: include/tvm/relay/op_attr_types.h
##
@@ -81,10 +81,16 @@ using TOpIsStateful = bool;
*/
using TNonComputational = bool;
+enum
schliffen opened a new issue #5449:
URL: https://github.com/apache/incubator-tvm/issues/5449
We are trying to convert a mxnet model into tvm (v7) in windows using the
following part of code:
loading model (works fine):
` mx_sym, args, auxs = mx.model.load_checkpoint(root +
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 37e5754 Improve IntervalSet's floormod (#5367)
add a60de36 [ONNX]GatherNd, Round, IsNaN, IsInf (#5445)
masahi commented on issue #5133:
URL: https://github.com/apache/incubator-tvm/issues/5133#issuecomment-619770517
@siju-samuel @woniuasd Since relay doesn't support in-place op, you cannot
use that python idiom.
This is an
100 matches
Mail list logo