leandron opened a new pull request #5466:
URL: https://github.com/apache/incubator-tvm/pull/5466
The `--cache-from` argument can be used on `buld.sh` to speed up the Docker
image (re)build process, by pointing to a remote image to be used as cache for
Docker layers.
This patch does
tqchen commented on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620649433
do a `git submodule update --init`
This is an automated message from the Apache Git Service.
To respond to the
zhiics commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620674803
Sorry for the late followup. I think both points make sense at certain
aspect. @manupa-arm I also think A1 should have been covered by binding
constants. Fixing constant
zhiics commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620687954
@mbaret yeah, I think that's generally good though. We can probably send an
RFC to see if we would break some other things. Otherwise, we can only bake it
into
zhiics edited a comment on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620687954
@mbaret yeah, I think that's generally good though. We can probably send an
RFC to see if we would break some other things as if it is usually the first
"pass" in
roastduck opened a new pull request #5465:
URL: https://github.com/apache/incubator-tvm/pull/5465
I added a new pass to convert `tvm_if_then_else` intrinsics to `IfThenElse`
statments. For example:
```c++
a[i] = tvm.te.if_then_else(x < y, x, y)
```
is now
```c++
tqchen commented on issue #5462:
URL: https://github.com/apache/incubator-tvm/issues/5462#issuecomment-620648810
Please open a new troubleshooting thread on https://discuss.tvm.ai/
This is an automated message from the
mbaret commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620684416
Explicitly binding constant tuples in the partitioner seems like a
reasonable solution. It would involve generalizing BindParamsByName to work
with tuples though (unless
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416614304
##
File path: tests/python/relay/test_op_level3.py
##
@@ -780,4 +826,5 @@ def verify_unravel_index(indices, shape, dtype):
test_gather_nd()
dreamqin68 commented on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620743607
> do a `git submodule update --init`
Thank you for your help.
I did `git submodule update --init`, then I rebuilt, `cmake ..`:
```
-- VTA build with
dreamqin68 removed a comment on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620743607
> do a `git submodule update --init`
Thank you for your help.
I did `git submodule update --init`, then I rebuilt, `cmake ..`:
```
-- VTA build
dreamqin68 commented on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620791750
> do a `git submodule update --init`
Thank you very much! It works.
This is an automated message
inadob commented on pull request #4805:
URL: https://github.com/apache/incubator-tvm/pull/4805#issuecomment-620736019
@anijain can you please help me with the quantized operators
This is an automated message from the Apache
wpan11nv commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416785651
##
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_r416785651
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] = {'x',
comaniac commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620711882
@manupa-arm I agree with your point and I prefer A1 more because it at least
maintains annotation pairs. A1 actually treats a constant node as an input
variable when
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 0a1e160 [Topi][Cuda]Optimizations of
zhiics edited a comment on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620886209
@MarisaKirisame Good question, I am not sure about how large it is.
@kevinthesun had a failed case. Maybe he can give a better answer.
MarisaKirisame commented on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620885344
@zhiics how big is a constant? is it ok to copy them around, or is any
tensor literal possible in there?
tqchen opened a new pull request #5469:
URL: https://github.com/apache/incubator-tvm/pull/5469
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
icemelon9 commented on a change in pull request #5459:
URL: https://github.com/apache/incubator-tvm/pull/5459#discussion_r417073724
##
File path: include/tvm/relay/attrs/transform.h
##
@@ -110,7 +110,7 @@ struct TakeAttrs : public tvm::AttrsNode {
/*! \brief Attributes that
This is an automated email from the ASF dual-hosted git repository.
zhaowu 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 a38f61a [Frontend][TFLite] L2_POOL_2D
zhiics edited a comment on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620886209
@MarisaKirisame Good question, I am not sure about how large it is.
@kevinthesun had a failed cased. Maybe he can give a better answer.
zhiics commented on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620886209
@MarisaKirisame Good question, I am not sure about large it is. @kevinthesun
had a failed cased. Maybe he can give a better answer.
roastduck commented on pull request #5465:
URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-620979160
Fixed. The problem was that some ops consist of too may `tvm_if_then_else`s,
such as `stride_set`. I added a threshold to control the max number of
`tvm_if_then_else`s
antinucleon opened a new pull request #5468:
URL: https://github.com/apache/incubator-tvm/pull/5468
asin
acos
acosh
asinh
atanh
atan
This is an automated message from the Apache Git Service.
To respond to the
roastduck edited a comment on pull request #5465:
URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-620979160
Fixed. The problem was that some ops consist of too may `tvm_if_then_else`s,
such as `stride_set`. The resulting number of branches increases exponentially
on
roastduck edited a comment on pull request #5465:
URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-620979160
Fixed. The problem was that some ops consist of too may `tvm_if_then_else`s,
such as `stride_set`. The resulting number of branches increases exponentially
on
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 2b32c95 [COMMUNITY] @liangfu ->
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 7060688 Improve Docker cache reuse by
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416996008
##
File path: python/tvm/exec/rpc_server.py
##
@@ -100,27 +101,34 @@ def server_shutdown():
parser.add_argument('--port-end', type=int,
tmoreau89 commented on pull request #5436:
URL: https://github.com/apache/incubator-tvm/pull/5436#issuecomment-620953773
@tqchen has the Docker image from #5437 been generated and updated in
Jenkins CI?
This is an automated
kevinthesun commented on pull request #5429:
URL: https://github.com/apache/incubator-tvm/pull/5429#issuecomment-620947544
cc @yongwww for another round of review.
This is an automated message from the Apache Git Service.
To
roastduck commented on pull request #5465:
URL: https://github.com/apache/incubator-tvm/pull/5465#issuecomment-620953848
Well, CI for Relay is broken. Closing this PR for now until I fix it.
This is an automated message from
MarisaKirisame commented on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620976285
I tooked a look at the discuss, and it seems like the way to fix it is to
just call ANF from Fold-Constant before going into the interpreter pass. can
you do that?
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416995111
##
File path: python/tvm/autotvm/measure/local_executor.py
##
@@ -145,6 +145,7 @@ def submit(self, func, *args, **kwargs):
if not
areusch commented on a change in pull request #5417:
URL: https://github.com/apache/incubator-tvm/pull/5417#discussion_r416998175
##
File path: python/tvm/exec/rpc_server.py
##
@@ -100,27 +101,34 @@ def server_shutdown():
parser.add_argument('--port-end', type=int,
kevinthesun opened a new pull request #5467:
URL: https://github.com/apache/incubator-tvm/pull/5467
Fix ShapeFuncRel for functions with mixed(tupletype and tensortype) inputs.
@icemelon9
This is an automated message
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r417026419
##
File path: src/relay/op/tensor/transform.cc
##
@@ -1891,81 +1952,163 @@ Array > StridedSliceInferCorrectLayout(
}
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 :
Menooker commented on a change in pull request #5357:
URL: https://github.com/apache/incubator-tvm/pull/5357#discussion_r417047631
##
File path: src/relay/transforms/fold_scale_axis.cc
##
@@ -39,6 +39,10 @@ namespace relay {
*
* Use namespace to reduce potential naming
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r417015283
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
MarisaKirisame commented on pull request #5457:
URL: https://github.com/apache/incubator-tvm/pull/5457#issuecomment-620973978
@zhiics I am not asking about the specific case here. I am asking that can
they be big.
IIRC, they can be arbitarily big, and it seems wrong to copy them.
westion717 opened a new issue #5464:
URL: https://github.com/apache/incubator-tvm/issues/5464
Hi, I find if use `directly 4 8 bit int in integer ` as following link, it
will cause compiling error (when the member of int is referred as .s0, .s1
later) in my opencl compiler provided by my
manupa-arm commented on pull request #5409:
URL: https://github.com/apache/incubator-tvm/pull/5409#issuecomment-620500976
I guess annotating backend-independent nodes (such as ConstantNodes,
TupleGetItem, Tuple, etc) are not trivial and they are special cased. Some
(e.g., TupleGetItem
siju-samuel opened a new pull request #5461:
URL: https://github.com/apache/incubator-tvm/pull/5461
- broadcast_plus
- broadcast_minus
- broadcast_power
- broadcast_logical_or
- broadcast_logical_and
- broadcast_logical_xor
- broadcast_to
- logical_not
-
maheshambule commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r416368690
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1770,6 +1775,12 @@ def convert_pool2d(self, op, pool_type):
assert
maheshambule commented on a change in pull request #5452:
URL: https://github.com/apache/incubator-tvm/pull/5452#discussion_r416368820
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -487,6 +487,31 @@ def test_forward_pooling():
dreamqin68 commented on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620430645
> vta-hw is a submodule, you may need 'git submodule init' and 'git
submodule update'
Thank you for your help.
Do you mean that Windows users who use Github
dreamqin68 edited a comment on issue #5440:
URL: https://github.com/apache/incubator-tvm/issues/5440#issuecomment-620430645
> vta-hw is a submodule, you may need 'git submodule init' and 'git
submodule update'
Thank you for your help.
Do you mean that Windows users who use
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416519580
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -2075,6 +2077,29 @@ def convert_space_to_depth(self, op):
return out
+
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416522181
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -2075,6 +2077,29 @@ def convert_space_to_depth(self, op):
return out
+
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416523256
##
File path: src/relay/op/tensor/transform.cc
##
@@ -2732,5 +2732,87 @@ Example::
.set_attr("FTVMCompute", UnRavelIndexCompute)
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416522950
##
File path: python/tvm/relay/op/transform.py
##
@@ -884,3 +884,29 @@ def unravel_index(indices, shape):
"""
return
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416523113
##
File path: src/relay/op/tensor/transform.cc
##
@@ -2732,5 +2732,87 @@ Example::
.set_attr("FTVMCompute", UnRavelIndexCompute)
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416524653
##
File path: topi/tests/python/test_topi_transform.py
##
@@ -595,6 +595,41 @@ def check_device(device):
for device in get_all_backend():
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416524442
##
File path: topi/include/topi/transform.h
##
@@ -1369,5 +1369,57 @@ inline Tensor one_hot(const Tensor& indices,
}, name, tag);
}
+/*!
+
dhruvaray commented on a change in pull request #5447:
URL: https://github.com/apache/incubator-tvm/pull/5447#discussion_r416524977
##
File path: topi/python/topi/transform.py
##
@@ -676,3 +676,30 @@ def unravel_index(indices, shape):
"""
return
boh-inspur commented on a change in pull request #5428:
URL: https://github.com/apache/incubator-tvm/pull/5428#discussion_r416455958
##
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_r416455958
##
File path: src/target/source/codegen_cuda.cc
##
@@ -274,9 +274,21 @@ void CodeGenCUDA::PrintVecElemLoad(
static const char access[] =
roastduck commented on pull request #5382:
URL: https://github.com/apache/incubator-tvm/pull/5382#issuecomment-620456420
@wpan11nv Could you explain how subgroups in OpenCL works? Up to now, we
always assumed `threadIdx.x` equals to warp in the `lower_warp_memory` pass.
Does it mean there
zoufangyu1987 opened a new issue #5462:
URL: https://github.com/apache/incubator-tvm/issues/5462
File "/data_1/TVM/TVM/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line
219, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
Pcheng-L opened a new issue #5463:
URL: https://github.com/apache/incubator-tvm/issues/5463
Thanks for participating in the TVM community! We use https://discuss.tvm.ai
for any general usage questions and discussions. The issue tracker is used for
actionable items such as feature
roastduck commented on a change in pull request #5345:
URL: https://github.com/apache/incubator-tvm/pull/5345#discussion_r416555638
##
File path: python/tvm/relay/qnn/op/legalizations.py
##
@@ -20,8 +20,8 @@
import tvm
from tvm import relay
+import numpy as np
Review
64 matches
Mail list logo