hcho3 edited a comment on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-616325899
I also tried building `ci-cpu` Docker image from scratch and running the
unit test inside the container. The test runs without crashing.
hcho3 commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-616325899
I also tried building `ci-cpu` Docker image from scratch and running the
unit test myself. The test runs without crashing.
siju-samuel opened a new pull request #5380:
URL: https://github.com/apache/incubator-tvm/pull/5380
Added support for merge operator `Minimum` and `AlphaDropout` in Keras
frontend.
@FrozenGene please help to review this PR and merge. Thanks.
hcho3 commented on issue #4953:
URL: https://github.com/apache/incubator-tvm/issues/4953#issuecomment-616318728
I compiled TVM from source and tried running the test
`tests/python/unittest/test_autotvm_xgboost_model.py::test_fit` and I cannot
reproduce the issue. Do I need a specific
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 4c0a53d [TIR][REFACTOR] RewriteForTensorCore -> te/schedule (#5379)
add 3f03869 [Blocksparse] Pipeline
antinucleon commented on issue #5377:
URL: https://github.com/apache/incubator-tvm/pull/5377#issuecomment-616310534
@vinx13 If directly convert a model from TensorFlow, like BERT, all dense
layers are in the format of ```y = nn.desnse(x, transpose(w))```. To further
convert it to a sparse
vinx13 commented on issue #5377:
URL: https://github.com/apache/incubator-tvm/pull/5377#issuecomment-616308977
Could you point out a scenario we need `simplify_fc_transpose`, even if we
already have `FoldConstant`?
This is
binarybana commented on a change in pull request #5328:
URL: https://github.com/apache/incubator-tvm/pull/5328#discussion_r411052316
##
File path: rust/tvm-rt/src/object.rs
##
@@ -0,0 +1,226 @@
+use std::ffi::{CString};
+use crate::Function;
+use tvm_sys::{TVMRetValue,
binarybana commented on a change in pull request #5328:
URL: https://github.com/apache/incubator-tvm/pull/5328#discussion_r411067781
##
File path: rust/tvm-rt/src/object.rs
##
@@ -0,0 +1,268 @@
+use std::convert::TryFrom;
+use std::convert::TryInto;
+use std::ffi::CString;
binarybana commented on a change in pull request #5328:
URL: https://github.com/apache/incubator-tvm/pull/5328#discussion_r411052316
##
File path: rust/tvm-rt/src/object.rs
##
@@ -0,0 +1,226 @@
+use std::ffi::{CString};
+use crate::Function;
+use tvm_sys::{TVMRetValue,
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411062353
##
File path: topi/python/topi/vision/nms.py
##
@@ -64,7 +67,56 @@ def hybrid_rearrange_out(data, one):
@hybrid.script
-def
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411062505
##
File path: topi/python/topi/vision/nms.py
##
@@ -139,24 +200,28 @@ def get_valid_counts(data, score_threshold=0, id_index=0,
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411062395
##
File path: topi/python/topi/vision/nms.py
##
@@ -64,7 +67,56 @@ def hybrid_rearrange_out(data, one):
@hybrid.script
-def
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411062313
##
File path: topi/python/topi/vision/nms.py
##
@@ -23,7 +23,7 @@
from ..sort import argsort
@hybrid.script
-def hybrid_rearrange_out(data,
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 22db299 [PYTORCH]Unary Ops (#5378)
add 4c0a53d [TIR][REFACTOR] RewriteForTensorCore -> te/schedule
binarybana commented on a change in pull request #5328:
URL: https://github.com/apache/incubator-tvm/pull/5328#discussion_r411052316
##
File path: rust/tvm-rt/src/object.rs
##
@@ -0,0 +1,226 @@
+use std::ffi::{CString};
+use crate::Function;
+use tvm_sys::{TVMRetValue,
This is an automated email from the ASF dual-hosted git repository.
masahi 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 22db299 [PYTORCH]Unary Ops (#5378)
masahi commented on issue #5378:
URL: https://github.com/apache/incubator-tvm/pull/5378#issuecomment-616266625
Nice! thanks @siju-samuel
This is an automated message from the Apache Git Service.
To respond to the message,
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411021266
##
File path: src/relay/transforms/fuse_ops.cc
##
@@ -247,6 +247,28 @@ class IndexedForwardGraph::Creator : private ExprVisitor {
kevinthesun commented on a change in pull request #4312:
URL: https://github.com/apache/incubator-tvm/pull/4312#discussion_r411020578
##
File path: src/relay/transforms/fuse_ops.cc
##
@@ -247,6 +247,28 @@ class IndexedForwardGraph::Creator : private ExprVisitor {
jwfromm commented on issue #5376:
URL: https://github.com/apache/incubator-tvm/pull/5376#issuecomment-616240213
@Hzfengsy, `conv2d` is already covered. I think all calls to tensorcore
schedules now check that `target==cuda`.
tqchen commented on issue #5379:
URL: https://github.com/apache/incubator-tvm/pull/5379#issuecomment-616235859
cc @Hzfengsy @minminsun @FrozenGene @yangjunpro @ZihengJiang @yzhliu
This is an automated message from the
tqchen opened a new pull request #5379:
URL: https://github.com/apache/incubator-tvm/pull/5379
RewriteForTensor depends on the schedule information, which makes it differ
from a typical pass(which should get all the information from the input TIR).
As a result, we refactor it as a
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 c3511c5 [TIR][REFACTOR] Remove
tqchen commented on issue #5376: [Relay][Strategy] Add cuda target check to
dense tensorcore schedule.
URL: https://github.com/apache/incubator-tvm/pull/5376#issuecomment-616200873
Thanks @jwfromm , @Hzfengsy can you double check if the conv2d case has been
fixed, and raise another PR if
tqchen closed issue #5370: Remove Interference of TensorCore Strategy to
OpenCL/Metal
URL: https://github.com/apache/incubator-tvm/issues/5370
This is an automated message from the Apache Git Service.
To respond to the
tqchen edited a comment on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178512
It would be great if we can dissect it down to specific cases in mind and
discuss how to solve these cases, I see two kinds of problems:
tqchen commented on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616182069
cc @Hzfengsy @yzhliu @hzfan
This is an automated message from the Apache Git
tqchen commented on a change in pull request #5367: Improve IntervalSet's
floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#discussion_r410945718
##
File path: src/arith/int_set.cc
##
@@ -372,7 +387,27 @@ class IntervalSetEvaluator :
}
IntervalSet
tqchen commented on a change in pull request #5367: Improve IntervalSet's
floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#discussion_r410945841
##
File path: src/arith/int_set.cc
##
@@ -730,12 +765,30 @@ Map ConvertDomMap(
return dmap;
}
-IntSet
tqchen commented on a change in pull request #5367: Improve IntervalSet's
floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#discussion_r410945647
##
File path: src/arith/int_set.cc
##
@@ -372,7 +387,27 @@ class IntervalSetEvaluator :
}
IntervalSet
tqchen edited a comment on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178512
It would be great if we can dissect it down to specific cases in mind and
discuss how to solve these cases, I see two kinds of problems:
tqchen edited a comment on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178512
It would be great if we can dissect it down to specific cases in mind and
discuss how to solve these cases, I see two kinds of problems:
tqchen commented on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178952
In particular, my comment wrt to EvalSet means we should directly use the
IntSetAnalyzer member of the analyzer, that can should have part of the
tqchen edited a comment on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178512
It would be great if we can dissect it down to specific cases in mind and
discuss how to solve these cases, I see two kinds of problems:
tqchen commented on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616178512
It would be great if we can dissect it down to specific cases in mind and
discuss how to solve these cases, I see two kinds of problems:
-
tqchen commented on a change in pull request #5367: Improve IntervalSet's
floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#discussion_r410941690
##
File path: include/tvm/te/operation.h
##
@@ -112,6 +113,7 @@ class OperationNode : public
ANSHUMAN87 commented on issue #5236: [WIP][TVM][.NET] Introduce TVM.NET project
URL: https://github.com/apache/incubator-tvm/pull/5236#issuecomment-616160551
> We can start code reviews and getting feedbacks from the community. Since
we do want to hold a high standard for new languauge
siju-samuel opened a new pull request #5378: [PYTORCH]Unary Ops frontend
support.
URL: https://github.com/apache/incubator-tvm/pull/5378
All unary ops support for pytorch frontend
@masahi Please help me to review this PR. Thanks.
yongfeng-nv edited a comment on issue #5367: Improve IntervalSet's floormod
URL: https://github.com/apache/incubator-tvm/pull/5367#issuecomment-616035227
The current behavior of IntervalSet floormod(a, b) is rough -- it returns
[0, b-1], [-b+1, b-1], or everything. It causes extra
mnboos commented on issue #2802: [BUILD]can't recognize llvm whem building
URL: https://github.com/apache/incubator-tvm/issues/2802#issuecomment-616092594
Line 9 of the error log says:
```
OpenCL_INCLUDE_DIR-NOTFOUND/CL/cl.h: No such file or directory
```
So the include
antinucleon opened a new pull request #5377: [Blocksparse] Pipeline for
lowering dense model to sparse-dense
URL: https://github.com/apache/incubator-tvm/pull/5377
Useful pass and helpful function to lower dense model to block sparse model.
In this PR it brings two new optimization
JishinMaster commented on issue #5376: [Relay][Strategy] Add cuda target check
to dense tensorcore schedule.
URL: https://github.com/apache/incubator-tvm/pull/5376#issuecomment-616048946
With your PR it worked for me with OpenCL and Vulkan backend.
It still fails with RoCM though, but
43 matches
Mail list logo