masahi commented on issue #13666:
URL: https://github.com/apache/tvm/issues/13666#issuecomment-1495370643
see https://github.com/apache/tvm/issues/13666#issuecomment-1397176511
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub a
wangzy0327 commented on issue #13666:
URL: https://github.com/apache/tvm/issues/13666#issuecomment-1495361255
@mvermeulen I execute ```rocminfo``` in docker rocm-tvm，but get error as
below.
```
root@0e7c68384def:/opt/rocm/bin# ./rocminfo
ROCk module is loaded
Unable to open /dev
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 8dea77a9ff [TOPI] dynamic externsion (#14450)
add 2c052b2067 [Frontend][Oneflow] Use FLOW_2_STR_DTYPE for dtype
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 4d7e890407 [testing] Use tuples for numpy indexing (#14476)
add 44dd6445ef [TensorIR] Support for L2 prefetch async
junrushao merged PR #14329:
URL: https://github.com/apache/tvm/pull/14329
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
from e54e04d520 [Unity][BYOC] Add cuBLAS backend (#14291)
add 5c2058dc3c [Unity][OP] Add `arange` op (#14463)
No new r
junrushao merged PR #14463:
URL: https://github.com/apache/tvm/pull/14463
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache
wangzy0327 commented on issue #13666:
URL: https://github.com/apache/tvm/issues/13666#issuecomment-1495285831
> [mvermeulen](/mvermeulen)
@mvermeulen hello，I tried to run the docker mevermeulen/rocm-tvm:5.4.2
with the python（anaconda conda virtual on host OS）, but I get the error.
jinhongyii commented on code in PR #14478:
URL: https://github.com/apache/tvm/pull/14478#discussion_r1156647265
##
src/runtime/relax_vm/attention_kv_cache.cc:
##
@@ -0,0 +1,162 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 8495335179 update image for ci_lint
discard d839db1132 trigger more run
add 91428158f2 [microTVM]Add
junrushao closed pull request #14453: [Doc] Publish MetaSchedule API Doc
URL: https://github.com/apache/tvm/pull/14453
--
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.
To unsubs
junrushao commented on PR #14453:
URL: https://github.com/apache/tvm/pull/14453#issuecomment-1495238295
Superseded by #14480
--
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.
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/unity by this push:
new e54e04d520 [Unity][BYOC] Add cuBLAS backend (#14291)
masahi merged PR #14291:
URL: https://github.com/apache/tvm/pull/14291
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
yongwww commented on code in PR #14481:
URL: https://github.com/apache/tvm/pull/14481#discussion_r1156632098
##
src/relax/op/tensor/index.cc:
##
@@ -47,11 +47,10 @@ StructInfo InferStructInfoTake(const Call& call, const
BlockBuilder& ctx) {
Array input_sinfo = GetInputTensor
tvm-bot commented on PR #14482:
URL: https://github.com/apache/tvm/pull/14482#issuecomment-1495222938
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
rebel-jangys opened a new pull request, #14482:
URL: https://github.com/apache/tvm/pull/14482
Here is the similar issue with Conv3Dtranspose #14340. Sending a PR to fix
this.
cc. @masahi
--
This is an automated message from the Apache Git Service.
To respond to the message, please
yongwww commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1155054422
##
python/tvm/script/parser/relax/parser.py:
##
@@ -220,7 +220,31 @@ def visit_tvm_declare_function(self: Parser, node:
doc.FunctionDef) -> GlobalVar
param_
sunggg closed pull request #14457: [Unity][Op] Dynamic Gather
URL: https://github.com/apache/tvm/pull/14457
--
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.
To unsubscribe, e-ma
sunggg commented on PR #14457:
URL: https://github.com/apache/tvm/pull/14457#issuecomment-1495219404
It turned out the semantic of onnx.gather is different with current
topi.gather that implements pytorch.gather.
Semantic of onnx.gather is closer to the special case of topi.take that
imp
sunggg commented on PR #14457:
URL: https://github.com/apache/tvm/pull/14457#issuecomment-1495219259
It turned out the semantic of `onnx.gather` is different with current
`topi.gather` that implements `pytorch.gather`.
Semantic of `onnx.gather` is closer to the special case of `topi.take
tvm-bot commented on PR #14481:
URL: https://github.com/apache/tvm/pull/14481#issuecomment-1495217687
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
sunggg opened a new pull request, #14481:
URL: https://github.com/apache/tvm/pull/14481
Currently, `relax.op.take` implements semantics of
[torch.take](https://pytorch.org/docs/stable/generated/torch.take.html) which
has a stronger restriction than its backing `topi.take` which seems to fol
tvm-bot commented on PR #14480:
URL: https://github.com/apache/tvm/pull/14480#issuecomment-1495206888
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
zxybazh opened a new pull request, #14480:
URL: https://github.com/apache/tvm/pull/14480
Following up #14453 to resolve issues in CI.
--
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
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 99a5734a9e [TIR] Add merge primitive for TIR schedule (#14398)
add 4d7e890407 [testing] Use tuples for numpy in
AndrewZhaoLuo merged PR #14476:
URL: https://github.com/apache/tvm/pull/14476
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.ap
This is an automated email from the ASF dual-hosted git repository.
wrongtest pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 76c8e66211 [Hexagon][TOPI] Use IndexMap axis separator instead of TE
(#14459)
add 99a5734a9e [TIR] Add merge primi
wrongtest-intellif merged PR #14398:
URL: https://github.com/apache/tvm/pull/14398
--
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.
To unsubscribe, e-mail: commits-unsubscr...@t
Hzfengsy commented on code in PR #14460:
URL: https://github.com/apache/tvm/pull/14460#discussion_r1156605159
##
python/tvm/relax/frontend/stablehlo/stablehlo_translator.py:
##
@@ -0,0 +1,417 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
tvm-bot commented on PR #14479:
URL: https://github.com/apache/tvm/pull/14479#issuecomment-1495161891
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
yongwww opened a new pull request, #14479:
URL: https://github.com/apache/tvm/pull/14479
add rsqrt to relax op, add rsqrt and sinh in legalizer
--
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
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a commit to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/unity by this push:
new 751da24bce [Unity][BYOC] Fix `RunCodegen` pass on symb
vinx13 merged PR #14472:
URL: https://github.com/apache/tvm/pull/14472
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
slyubomirsky commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1156524973
##
src/relax/op/op.cc:
##
@@ -177,7 +227,9 @@ TVM_REGISTER_OP("relax.call_builtin_with_ctx")
.set_num_inputs(4)
.add_argument("func", "Expr", "The builtin
masahi commented on PR #14474:
URL: https://github.com/apache/tvm/pull/14474#issuecomment-1495082637
Is this specific to Unity?
--
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
tqchen merged PR #14473:
URL: https://github.com/apache/tvm/pull/14473
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
from db01567b09 [Unity][Op] introduce `shape_to_tensor` op (#14447)
add ea56542f96 [Unity][CI] Update gpu and lint image (
tqchen commented on PR #14470:
URL: https://github.com/apache/tvm/pull/14470#issuecomment-1495062724
We can temp disable rust tests to unlock CI
--
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 t
tqchen opened a new pull request, #14478:
URL: https://github.com/apache/tvm/pull/14478
This PR provides a simple implementation of inplace attention kv cache for
relax runtime. The main goal here is to help us enable auto-regressive decoding
quickly in relax.
This is likely not the
tvm-bot commented on PR #14478:
URL: https://github.com/apache/tvm/pull/14478#issuecomment-1495035667
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
tvm-bot commented on PR #14477:
URL: https://github.com/apache/tvm/pull/14477#issuecomment-1494990326
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
This is an automated email from the ASF dual-hosted git repository.
kparzysz pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 2c052b2067 [Frontend][Oneflow] Use FLOW_2_STR_DTYPE for dtype (#14454)
add 76c8e66211 [Hexagon][TOPI] Use IndexMap a
kparzysz-quic merged PR #14459:
URL: https://github.com/apache/tvm/pull/14459
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.ap
kparzysz-quic commented on PR #14469:
URL: https://github.com/apache/tvm/pull/14469#issuecomment-1494970633
The CPU build failure is due to
```
failed to fetch
`[https://github.com/rust-lang/crates.io-index`](https://github.com/rust-lang/crates.io-index%60)
```
--
This is an auto
kparzysz-quic commented on PR #14470:
URL: https://github.com/apache/tvm/pull/14470#issuecomment-1494970351
The CPU build failure is due to
```
failed to fetch
`[https://github.com/rust-lang/crates.io-index`](https://github.com/rust-lang/crates.io-index%60)
```
--
This is an auto
tvm-bot commented on PR #14476:
URL: https://github.com/apache/tvm/pull/14476#issuecomment-1494963864
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
kparzysz-quic opened a new pull request, #14476:
URL: https://github.com/apache/tvm/pull/14476
Some versions of numpy disallow the following:
```
>>> import numpy as np
>>> a = np.zeros(10)
>>> b = [slice(None)]
>>> a[b]
Traceback (most recent call last):
File "", l
kparzysz-quic opened a new pull request, #14475:
URL: https://github.com/apache/tvm/pull/14475
Pytest expects test functions to return None, and errors to be flagged via
exceptions. It actually emits warnings for "return" statements encountered in
test_ functions.
--
This is an automated
tvm-bot commented on PR #14475:
URL: https://github.com/apache/tvm/pull/14475#issuecomment-1494962733
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
tvm-bot commented on PR #14474:
URL: https://github.com/apache/tvm/pull/14474#issuecomment-1494954885
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
kparzysz-quic opened a new pull request, #14474:
URL: https://github.com/apache/tvm/pull/14474
Everything is expected to be either te.Tensor, or a PrimExpr, so make sure
that function parameters conform to that. Also, remove incorrect type
annotations from `qnn_requantize`.
--
This is an
psrivas2 commented on code in PR #14465:
URL: https://github.com/apache/tvm/pull/14465#discussion_r1156430949
##
src/relax/backend/contrib/cutlass/codegen.cc:
##
@@ -219,11 +219,16 @@ class CodegenCutlass : public
relax::MemoizedExprTranslator,
class CutlassModuleCodegen {
masahi commented on code in PR #14465:
URL: https://github.com/apache/tvm/pull/14465#discussion_r1156423599
##
src/relax/backend/contrib/cutlass/codegen.cc:
##
@@ -219,11 +219,16 @@ class CodegenCutlass : public
relax::MemoizedExprTranslator,
class CutlassModuleCodegen {
p
tqchen commented on PR #14473:
URL: https://github.com/apache/tvm/pull/14473#issuecomment-1494932944
indeed a branch in apache would be the way to go, normally we use
unity-staging for that
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
masahi commented on PR #14465:
URL: https://github.com/apache/tvm/pull/14465#issuecomment-1494927124
Actually, since `compile_cutlass_module` is also used by the Relax BYOC, I
think we are already making use of `-t` flag. And putting all sources into a
single source module is the right solu
adstraw closed pull request #14288: Rewrite and simplify after
InjectSoftwarePipeline to reduce mem footprint
URL: https://github.com/apache/tvm/pull/14288
--
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
masahi commented on PR #14465:
URL: https://github.com/apache/tvm/pull/14465#issuecomment-1494922361
`-t` flag is the number of threads to use for NVCC,
https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/#threads-number-t. This
is used by the Relay BYOC to compile all files in parallel.
psrivas2 commented on PR #14465:
URL: https://github.com/apache/tvm/pull/14465#issuecomment-1494910975
> The original intention was to compile all generated files in parallel (via
NVCC `-t` flag), but I forgot to actually do it. Have you tested that? I expect
that would be faster than this
tvm-bot commented on PR #14473:
URL: https://github.com/apache/tvm/pull/14473#issuecomment-1494856866
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch ci-update-cuda
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 2341755b10f967d38cf6d954f1c3aabf64af6dcf
Author: Masahiro Masuda
AuthorDate: Tue Apr 4 04:24:17 2023 +0900
upd
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch ci-update-cuda
in repository https://gitbox.apache.org/repos/asf/tvm.git
at 2341755b10 update GPU and lint image
This branch includes the following new commits:
new 2341755b10 update
tvm-bot commented on PR #14472:
URL: https://github.com/apache/tvm/pull/14472#issuecomment-1494841848
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
masahi opened a new pull request, #14472:
URL: https://github.com/apache/tvm/pull/14472
BYOC tests using symbolic shapes have been broken since
https://github.com/apache/tvm/pull/14396
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
masahi closed pull request #14471: [Unity][BYOC] Fix `RunCodegen` pass on
symbolic output shape
URL: https://github.com/apache/tvm/pull/14471
--
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 spec
tvm-bot commented on PR #14471:
URL: https://github.com/apache/tvm/pull/14471#issuecomment-1494839442
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
masahi opened a new pull request, #14471:
URL: https://github.com/apache/tvm/pull/14471
BYOC tests using symbolic shapes have been broken since
https://github.com/apache/tvm/pull/14396
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
tvm-bot commented on PR #14470:
URL: https://github.com/apache/tvm/pull/14470#issuecomment-1494835966
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
kparzysz-quic opened a new pull request, #14470:
URL: https://github.com/apache/tvm/pull/14470
These functions are virtual, and some of the overrides were not marked as
either `final` or `override` causing compilation warnings.
--
This is an automated message from the Apache Git Service.
tvm-bot commented on PR #14469:
URL: https://github.com/apache/tvm/pull/14469#issuecomment-1494835649
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
kparzysz-quic opened a new pull request, #14469:
URL: https://github.com/apache/tvm/pull/14469
The file llvm/Transforms/IPO/PassManagerBuilder.h has been removed in LLVM
17, as a part of the transition to the new pass manager. Add a LLVM version
guard around the #include.
--
This is an a
masahi commented on PR #14465:
URL: https://github.com/apache/tvm/pull/14465#issuecomment-1494833971
The original intention was to compile all generated files in parallel (via
NVCC `-t` flag), but I forgot to actually do it. Have you tested that? I expect
that would be faster than this solu
tqchen closed issue #13876: [Tracking Issue] Unity Branch Establishment
URL: https://github.com/apache/tvm/issues/13876
--
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.
To unsub
tqchen commented on issue #13876:
URL: https://github.com/apache/tvm/issues/13876#issuecomment-1494804540
Thanks to everyone's effort, the unity branch is now established. Closing
this issue for now. We can open future issues to track specific items for unity
component developments
--
Th
tvm-bot commented on PR #14468:
URL: https://github.com/apache/tvm/pull/14468#issuecomment-1494799897
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
cbalint13 opened a new pull request, #14468:
URL: https://github.com/apache/tvm/pull/14468
This PR fix the latest xgboost >= 1.7.5 behaviour requiring binarized labels.
* The strict behaviour was introduced by
https://github.com/dmlc/xgboost/pull/8931
* A possible solution (also
[
slyubomirsky commented on PR #14394:
URL: https://github.com/apache/tvm/pull/14394#issuecomment-1494754362
Tests failing due to the rebase (have to update some more ops/passes), will
address shortly.
--
This is an automated message from the Apache Git Service.
To respond to the message, p
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a commit to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/unity by this push:
new db01567b09 [Unity][Op] introduce `shape_to_tensor` op
vinx13 merged PR #14447:
URL: https://github.com/apache/tvm/pull/14447
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 1527bfba04 [TVMScript][Bugfix] Tuple on the RHS of AssignDoc (#14452)
add 97ab25c33f [Unity][BYOC] Faster cutlass code
vinx13 merged PR #14465:
URL: https://github.com/apache/tvm/pull/14465
--
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.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
zxybazh commented on PR #14456:
URL: https://github.com/apache/tvm/pull/14456#issuecomment-1494702016
I think the only difference here is definition of target host, the current
`TVM_REGISTER_CUDA_TAG` macro doesn't involve target host definition. Please
feel free to send a PR to add host de
slyubomirsky commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1156222367
##
python/tvm/script/parser/relax/parser.py:
##
@@ -220,7 +220,31 @@ def visit_tvm_declare_function(self: Parser, node:
doc.FunctionDef) -> GlobalVar
p
slyubomirsky commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1156214386
##
src/relax/op/op.cc:
##
@@ -177,7 +227,9 @@ TVM_REGISTER_OP("relax.call_builtin_with_ctx")
.set_num_inputs(4)
Review Comment:
Good observation
--
This
slyubomirsky commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1156214194
##
python/tvm/relax/analysis/analysis.py:
##
@@ -276,6 +276,34 @@ def has_reshape_pattern(func: tir.PrimFunc) -> bool:
return _ffi_api.has_reshape_pattern(func)
slyubomirsky commented on code in PR #14394:
URL: https://github.com/apache/tvm/pull/14394#discussion_r1156213743
##
src/relax/op/tensor/manipulate.cc:
##
@@ -1357,7 +1370,8 @@ TVM_REGISTER_OP("relax.cumsum")
.set_attrs_type()
.set_num_inputs(1)
.add_argument("dat
tvm-bot commented on PR #14467:
URL: https://github.com/apache/tvm/pull/14467#issuecomment-1494638500
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
psrivas2 opened a new pull request, #14467:
URL: https://github.com/apache/tvm/pull/14467
cc @junrushao @vinx13
--
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.
To unsubscr
abhikran-quic commented on PR #14459:
URL: https://github.com/apache/tvm/pull/14459#issuecomment-1494538738
cc: @masahi @kparzysz-quic
--
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 specifi
yongwww commented on PR #14457:
URL: https://github.com/apache/tvm/pull/14457#issuecomment-1494523707
it would be good to add some tests in
`tests/python/topi/python/test_topi_transform.py` as well.
--
This is an automated message from the Apache Git Service.
To respond to the message, p
tvm-bot commented on PR #14466:
URL: https://github.com/apache/tvm/pull/14466#issuecomment-1494485601
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
multiverstack-intellif opened a new pull request, #14466:
URL: https://github.com/apache/tvm/pull/14466
Update docker image tag as a follow up step for
https://github.com/apache/tvm/pull/14303.
--
This is an automated message from the Apache Git Service.
To respond to the message, please
junrushao commented on PR #14329:
URL: https://github.com/apache/tvm/pull/14329#issuecomment-1494437786
Please remove code instead of commenting them out :-)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL abov
Lunderberg closed pull request #14318: [Bugfix][TVMScript] Preserve foldable
constants while parsing
URL: https://github.com/apache/tvm/pull/14318
--
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
Lunderberg commented on PR #14318:
URL: https://github.com/apache/tvm/pull/14318#issuecomment-1494401402
Looks like #14320 has been merged (thank you @junrushao !), closing this PR.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Git
tvm-bot commented on PR #14465:
URL: https://github.com/apache/tvm/pull/14465#issuecomment-1494399612
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
psrivas2 opened a new pull request, #14465:
URL: https://github.com/apache/tvm/pull/14465
This PR improves cutlass compilation time, by compiling a single
CSourceModule instead of creating and compiling one for each kernel.
Creating and compiling a new CSourceModule for every function
Aleksei-grovety commented on code in PR #14464:
URL: https://github.com/apache/tvm/pull/14464#discussion_r1156001266
##
tests/python/contrib/test_ethosu/test_layout_optimizer.py:
##
@@ -121,6 +121,44 @@ def get_graph():
_assert_structural_equal(a, b)
+@pytest.mark.param
ilyag-grovety commented on code in PR #14464:
URL: https://github.com/apache/tvm/pull/14464#discussion_r1155930099
##
tests/python/contrib/test_ethosu/test_layout_optimizer.py:
##
@@ -121,6 +121,44 @@ def get_graph():
_assert_structural_equal(a, b)
+@pytest.mark.paramet
masahi commented on PR #14396:
URL: https://github.com/apache/tvm/pull/14396#issuecomment-149488
The fix has been added in the PR https://github.com/apache/tvm/pull/14291
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub an
1 - 100 of 132 matches
Mail list logo
