Merge OpenAI Triton commit `16ce143`#2807

Merged

whitneywhtsang merged 14 commits intomainfrom

whitneywhtsang/merge

Nov 23, 2024

Commits on Nov 22, 2024

[BACKEND] Fix transpose optimization missed during refactor (#5226)
ThomasRaoux
authored
[AMD] Use warp shuffle for fp8 MFMA to dot operand layout conversion (#5139)
ilia-cher
authored
[LAYOUTS] [BE] Simplify Ampere/Hopper paths introduced in #5189 (#5200)
lezcano
authored
[BACKEND] Use LL to simplify redundant elements check and fix related issues (#5225)
Jokeren
authored
Make TMA tests compatible with older CUDA toolchains (#5221)
embg
authored
[CMake] Add C as project language (#5217)
makslevental
authored
[AMD] Fix slow compilation due to inlining print calls (#5153)

binarman
and
antiagainst
authored
[AMD] Re-enable overflow test in test_reduce_layouts (#5233)
antiagainst
authored
Merge commit '4ae95e70cd81eb62f89ec530605440b85e799dee'
whitneywhtsang
committed
Merge commit '16ce143b54eacf465c5a90a6aabdc9c3a723cb99'
whitneywhtsang
committed