This is an automated email from the ASF dual-hosted git repository.
syfeng pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new a9436b8154 [Fix][Builtin] Fix "GetQueryPosition" of Pag
Hzfengsy merged PR #16746:
URL: https://github.com/apache/tvm/pull/16746
--
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.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 95ec38be98 [Arith] Provide tighter ConstIntBounds for special cases
(#16588)
add 8b5bd555d1 [Target][CUDA] All
csullivan closed pull request #16638: [CMAKE][CUTLASS] Improve dependency
management
URL: https://github.com/apache/tvm/pull/16638
--
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 comme
MasterJH5574 opened a new pull request, #16752:
URL: https://github.com/apache/tvm/pull/16752
Prior to this PR, module "psutil" is imported at the top level of the disco
process pool. The pool will try to kill all the processes at the time of
destruction (when `__del__` is implicitly invoke
vinx13 opened a new pull request, #16751:
URL: https://github.com/apache/tvm/pull/16751
This adds sm90a group gemm kernels from cutlass. It includes cmake
improvement from #16638 .
Supersedes #16638.
Co-authored-by: Chris Sullivan
Co-authored-by: masahi
cc @csulliv
slyubomirsky commented on PR #16744:
URL: https://github.com/apache/tvm/pull/16744#issuecomment-2008297192
I think this idea is very promising, though we should be certain of some
corners of the design:
1. Is there any invariant we want to unknown purity? Do we expect all
unknown puritie
tqchen commented on code in PR #16750:
URL: https://github.com/apache/tvm/pull/16750#discussion_r1531208339
##
src/runtime/disco/cuda_ipc/custom_allreduce.cc:
##
@@ -0,0 +1,80 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license a
tqchen commented on code in PR #16750:
URL: https://github.com/apache/tvm/pull/16750#discussion_r1531200356
##
src/runtime/disco/cuda_ipc/cuda_ipc_memory.cc:
##
@@ -0,0 +1,212 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license a
jinhongyii commented on code in PR #16750:
URL: https://github.com/apache/tvm/pull/16750#discussion_r1531075541
##
tests/python/disco/test_custom_allreduce.py:
##
@@ -0,0 +1,59 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreem
MasterJH5574 opened a new pull request, #16750:
URL: https://github.com/apache/tvm/pull/16750
This PR introduces the CUDA IPC memory support in TVM runtime. IPC memory
allows multiple distribtued workers accessing the GPU memory of each other
directly. This functionality is helpful for impl
thaisacs commented on PR #16739:
URL: https://github.com/apache/tvm/pull/16739#issuecomment-2007794939
@merrymercy do you think that this make sense?
--
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
This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from ff6ce9c2b3 Enable Shared Function in LiftTransformParam Pass (#16717)
add 48cedc7d2e [Arith][Fixup] Require feature fla
vinx13 merged PR #16735:
URL: https://github.com/apache/tvm/pull/16735
--
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 commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new ff6ce9c2b3 Enable Shared Function in LiftTransformParam
vinx13 merged PR #16717:
URL: https://github.com/apache/tvm/pull/16717
--
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
Lunderberg commented on PR #16745:
URL: https://github.com/apache/tvm/pull/16745#issuecomment-2007472782
@tvm-bot rerun
--
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 u
lhutton1 opened a new pull request, #16749:
URL: https://github.com/apache/tvm/pull/16749
This commit adds the infrastructure required for testing compiled functions
that use SME. A more in depth discussion can be found here:
https://github.com/apache/tvm-rfcs/blob/main/rfcs/0107-scalable-m
Lunderberg opened a new pull request, #16748:
URL: https://github.com/apache/tvm/pull/16748
Prior to this commit, the `CodeGenLLVM::GetDebugType` would raise an
exception if it could not convert the TIR data type to an equivalent DWARF type
for debug symbols. This commit updates the behavi
This is an automated email from the ASF dual-hosted git repository.
lukhut pushed a change to branch
Add_PyTorch_and_ONNX_tests_enablement_to_AArch64
in repository https://gitbox.apache.org/repos/asf/tvm.git
at 2e5230bdad Enable ONNX and PyTorch tests on AArch64
No new revisions were add
tqchen commented on PR #16747:
URL: https://github.com/apache/tvm/pull/16747#issuecomment-2007354043
I think we should actually avoid running exccessive integration tests across
platforms. The unit tests of frontend should only cover the ingestion part.
While the UT of the backend should b
Liam-Sturge opened a new pull request, #16747:
URL: https://github.com/apache/tvm/pull/16747
This makes use of work done in enabling PyTorch and ONNX tests to be run on
AArch64 to actually enable the tests to run as part of CI.
Co-Authored-By: Nicola Lancellotti
[nicola.lancello...@a
MasterJH5574 opened a new pull request, #16746:
URL: https://github.com/apache/tvm/pull/16746
Since #16692 introduced the copy stream separation, the function
`GetQueryPositions` also needs to eagerly call sync to work properly. This PR
fixes the previous wrong behavior.
--
This is an au
Lunderberg opened a new pull request, #16745:
URL: https://github.com/apache/tvm/pull/16745
Prior to this commit, the default `DictAttrs` for an `IRModule`,
`tir::PrimFunc`, `relax::Function`, and `relay::Function` was a null value. At
each callsite, the absence of a `DictAttrs` needed to
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 97d92b5483 [Refactor][Runtime] Always specify device in allocator
interface (#16738)
add 7641c6e20e [CLML] Fix build
tqchen merged PR #16672:
URL: https://github.com/apache/tvm/pull/16672
--
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 main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 8b5bd555d1 [Target][CUDA] Allow non-numeric arch as needed for latest
gpu (#16736)
add 97d92b5483 [Refactor][Runtime]
tqchen merged PR #16738:
URL: https://github.com/apache/tvm/pull/16738
--
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
tqchen commented on issue #16707:
URL: https://github.com/apache/tvm/issues/16707#issuecomment-2007135658
@Lunderberg given you introduced python trace, can you help on this one ?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHu
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 95ec38be98 [Arith] Provide tighter ConstIntBounds for special cases
(#16588)
add 8b5bd555d1 [Target][CUDA] Allow non-
tqchen merged PR #16736:
URL: https://github.com/apache/tvm/pull/16736
--
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
Lunderberg commented on PR #16687:
URL: https://github.com/apache/tvm/pull/16687#issuecomment-2007119438
I like it, and I've made a sibling PR
https://github.com/apache/tvm/pull/16744 that would allow `FuncStructInfo` to
describe a function with unknown purity. There's a couple of common e
Cilouche opened a new issue, #16743:
URL: https://github.com/apache/tvm/issues/16743
Hi
I use conda under windows for a development environment, I encounter a
problem with TVM, namely that I have performed all the installation steps the
error below
![image](https://github.co
qsqqsqqsq-intellif opened a new pull request, #16742:
URL: https://github.com/apache/tvm/pull/16742
Prior to this commit, cache_read primitive may not update the block reads
buffer region properly when there is a nested buffer access.
`for ax0, ax1 in T.grid(T.int64(1), T.int64(512)):
This is an automated email from the ASF dual-hosted git repository.
leandron pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git
The following commit(s) were added to refs/heads/main by this push:
new 176a14e [RFC] Scalable Matrix Extension enablem
leandron merged PR #107:
URL: https://github.com/apache/tvm-rfcs/pull/107
--
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
leandron commented on PR #107:
URL: https://github.com/apache/tvm-rfcs/pull/107#issuecomment-2006481419
This has been approved a few days back, so merging it now so that we
continue the discussions in the context of the tracking issue and upcoming PRs.
Thank you for all the discussion
apeskov opened a new pull request, #16741:
URL: https://github.com/apache/tvm/pull/16741
Unfortunately, relax GPU tests are excluded from CI right now.
The testing script uses flag "-m gpu" to run gpu tests, but actual tests
have no such mark.
--
This is an automated message from the
Cavan1Ed1s0n opened a new issue, #16740:
URL: https://github.com/apache/tvm/issues/16740
I installed tvm from the source in order to deploy model on mali GPU but it
raised this error. I found the similar error in github but there isn't anyone
solve it. Is there anyone can help me?
module
39 matches
Mail list logo