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 f9e36fcbf8 [3rdparty] Bump FlashInfer (#16866)
add c67a055386 [BugFix][Target] Added null check to fix segfault
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch dependabot/pip/apps/microtvm/idna-3.7
in repository https://gitbox.apache.org/repos/asf/tvm.git
at 557d185544 Bump idna from 3.4 to 3.7 in /apps/microtvm
No new revisions were added by
dependabot[bot] opened a new pull request, #16875:
URL: https://github.com/apache/tvm/pull/16875
Bumps [idna](https://github.com/kjd/idna) from 3.4 to 3.7.
Release notes
Sourced from https://github.com/kjd/idna/releases";>idna's
releases.
v3.7
What's Changed
Fix is
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch dependabot/pip/docker/python/idna-3.7
in repository https://gitbox.apache.org/repos/asf/tvm.git
at 4fdd576c8a Bump idna from 3.3 to 3.7 in /docker/python
No new revisions were added by
dependabot[bot] opened a new pull request, #16874:
URL: https://github.com/apache/tvm/pull/16874
Bumps [idna](https://github.com/kjd/idna) from 3.3 to 3.7.
Release notes
Sourced from https://github.com/kjd/idna/releases";>idna's
releases.
v3.7
What's Changed
Fix is
This is an automated email from the ASF dual-hosted git repository.
tqchen 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 88a1c6560c [3rdparty] Bump flashinfer (#16868)
88a1c656
tqchen merged PR #16868:
URL: https://github.com/apache/tvm/pull/16868
--
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 merged PR #16871:
URL: https://github.com/apache/tvm/pull/16871
--
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 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 0aae97d8e4 [PageKV] allow PopN to pop all the tokens in
MasterJH5574 commented on PR #16873:
URL: https://github.com/apache/tvm/pull/16873#issuecomment-2050554844
Thanks! Could you also enlarge the workspace estimation? 2n is not enough
for sort based on our observation. Likely at least 8n with additional 4MB is
needed.
--
This is an automate
vinx13 opened a new pull request, #16873:
URL: https://github.com/apache/tvm/pull/16873
cc @tqchen @MasterJH5574
--
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 unsubsc
MasterJH5574 opened a new pull request, #16872:
URL: https://github.com/apache/tvm/pull/16872
This PR enhances the symbolic expression upper bound estimation in static
memory planning.
Prior to this PR, we are not able to estimate the upper bound of `a * b`
when `a` has an upper boun
agoston-mc opened a new pull request, #108:
URL: https://github.com/apache/tvm-rfcs/pull/108
A RFC to add a Neural Network Exchange Format frontend to TVM relay.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
JamesSand commented on issue #13595:
URL: https://github.com/apache/tvm/issues/13595#issuecomment-2050144119
same issue +1
--
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.
T
KnowingNothing opened a new pull request, #16871:
URL: https://github.com/apache/tvm/pull/16871
In some scenarios such as speculative decoding, it is possible to pop all
the tokens in the last block. This PR allows `PopN` to pop all the tokens in
the last block of KV cache.
--
This is an
ekalda commented on code in PR #16862:
URL: https://github.com/apache/tvm/pull/16862#discussion_r1560717574
##
tests/python/arith/test_arith_simplify.py:
##
@@ -53,6 +56,33 @@ def test_simplify_symbolic_comparison():
assert ana.can_prove((n + 31) // 32 * 32 >= i0 * 32 + i1,
tqchen merged PR #16854:
URL: https://github.com/apache/tvm/pull/16854
--
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 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 4b906554af [OpenCL] Add OpenCL device for automatic tar
tqchen commented on PR #16868:
URL: https://github.com/apache/tvm/pull/16868#issuecomment-2049453740
@vinx13 we can disable the flaky test
--
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
Jupiterghy opened a new issue, #16870:
URL: https://github.com/apache/tvm/issues/16870
When applying optimization passes in TVM, there is a discrepancy in the
results between directly applying opt_a(opt_b(mod)) and using a sequential
optimization approach, where seq_ab = tvm.ir.transform.Se
Jupiterghy opened a new issue, #16869:
URL: https://github.com/apache/tvm/issues/16869
When attempting to compile the model after applying LazyGradientInit
optimization passes in TVM, an error is encountered:
```
tvm.error.InternalError: Check failed: (it != type_definitions.end()) is
This is an automated email from the ASF dual-hosted git repository.
lukhut 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 c67a055386 [BugFix][Target] Added null check to fix seg
lhutton1 commented on PR #16766:
URL: https://github.com/apache/tvm/pull/16766#issuecomment-2049162856
Thanks @OttoWRas!
--
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
lhutton1 merged PR #16766:
URL: https://github.com/apache/tvm/pull/16766
--
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.
masahi closed issue #13173: [Bug] VTA FSIM MacOS incompatibility
URL: https://github.com/apache/tvm/issues/13173
--
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,
25 matches
Mail list logo