Skip to content

Tags: NVIDIA/cutlass

Tags

v4.8.0dev

Toggle v4.8.0dev's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
v4.8 dev update. (#3551)

v4.7.1

Toggle v4.7.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
v4.7.1 update (#3550)

Co-authored-by: Shreya Gaur <shgaur@dc2-container-xterm-006.prd.it.nvidia.com>

v4.6.3

Toggle v4.6.3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
v4.6.3 update (#3548)

Co-authored-by: Shreya Gaur <shgaur@dc2-container-xterm-006.prd.it.nvidia.com>

v4.7.0

Toggle v4.7.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #3289 from kainzhong/more_tvm_ffi_doc

[CuTeDSL] Add docs of how to call cute.jit functions in C++ via TVM-FFI

v4.6.2

Toggle v4.6.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
v4.6.2 update. (#3434)

v4.6.1

Toggle v4.6.1's commit message
v4.6.1 update. (#3383)

* v4.6.1 update.

* Correct version number.

* Fix documentation link for GEMM performance measurement

Updated the link in the documentation release note for GEMM performance measurement methodology.

* Fix URL in 'What's New in CUTLASS 4.6' section

Corrected the URL for GEMM performance measurement documentation.

---------

Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>

v4.6.0

Toggle v4.6.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
update changelog.md (#3375)

* update changelog.md

* more changes

v4.5.3

Toggle v4.5.3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
v4.5.3 update. (#3371)

v4.2.2

Toggle v4.2.2's commit message
add one more item in changelog

v4.3.6

Toggle v4.3.6's commit message
port nvrtc change to version.h

update to 4.3.6

alignment-related miscalculation for pipeline stages

Allow larger library on 64bit platform

add more changelog items

remove whitespace