Bump triton from 3.6.0 to 3.7.0 in /tools/ci

[dependabot]

Bumps triton from 3.6.0 to 3.7.0.

Release notes

Sourced from triton's releases.

Triton 3.7 Release Notes

Table of Contents

• Dialect & Frontend
• Backend & Compiler
• AMD/HIP Backend
• NVIDIA Backend
• Gluon & Layout Improvements
• Kernels & Benchmarks
• Proton Profiling
• Testing & CI
• Build & Infrastructure
• Documentation
• Breaking Changes
• Contributors

---

Dialect & Frontend

New Features

• tl.squeeze / tl.unsqueeze: Added tl.squeeze and tl.unsqueeze operations to the standard library (#8924)
• Scaled BMM: Added support for scaled batched matmul in the frontend (#9000)
• FP8 Constants: Frontend can now create FP8 constants directly (#8882)
• Returning Constexpr from JIT: Functions can return constexpr values from JIT-compiled code (#8785)
• get_int_attr for Out-of-Tree Walk: Added get_int_attr to Operation to support out-of-tree IR walks (#8892)
• Optional Device Arg to preload: Added optional device argument to preload and guardrails for cross-target preload (#8951, #8952, #9234)
• tl.cat(can_reorder=False): Added a non-reordering variant of tl.cat with broadcast support (#9312, #9163)
• Round f32→tf32 in Descriptor: Added option to round f32 to tf32 inside tensor descriptors (#9295)
• Plugin Hooks & Out-of-Tree Dialects: Added support for out-of-tree TTIR/TTGIR passes and Triton Dialect Plugins, with example documentation (#8401, #8523, #8815)

Bug Fixes

• desc.shape for FP4 Padded: Fixed desc.shape values for fp4-padded tensor descriptors (#9012)
• Setting Attr on Constexpr Argument: Fixed setting attributes on constexpr arguments (#9053)
• Named Tuples in Constexpr Functions: Preserved named tuples through constexpr_functions (#8876)
• must_use_result for Methods: Fixed must_use_result check for methods (#8902)
• _semantic Default to None: Defaulted _semantic parameter to None (#8909)
• make_tensor_descriptor Error Typo: Fixed typo in make_tensor_descriptor error message (#8912)
• tl.cat Determinism: Made tl.cat deterministic via permute+reshape+join, then reverted (#9312, #8854, #8878)
• Deprecation Warning for make_block_ptr: Emitted a deprecation warning when make_block_ptr is used (#9667)

Improvements

• Frontend Performance: Pre-computed inspect.signature for builtins, lazily computed tuple type names, avoided find_paths_if and inspect.getclosurevars, removed outdated catch_warnings blocks — all to reduce JIT overhead (#8843, #8844, #8846, #8845, #8881)
• Revert Deep Copy on Scope Entry: Removed deep copy when entering a new scope (#8832)
• Default 32-bit Dot Precision Change: Briefly changed default 32-bit dot precision to TF32x3, then reverted (#9080, #9090)
• Tutorial Updates (#8565, #8853, #8982)
• Interpreter Cleanups: Typing and efficiency cleanups in the interpreter (#9072)

---

Backend & Compiler

... (truncated)

Commits

• 5f3f125 [release 3.7] Release Triton to pypi (#10251)
• ecbbf0e [CD][Release Only] Increase timeout for Release wheels (#10250)
• 8a1faba [release/3.7.x][CI] Reduce wheel size and pin DOCKER_API_VERSION (#10244)
• b7fa781 [release/3.7.x] Cherry pick "Split RemoveLayoutConversions cleanup so scf.if ...
• 88b227e [release/3.7.x][AMD][BACKEND] Fix mixed FP8 types promotion for WMMA (#9581) ...
• 6520a28 [release/3.7.x][AMD][BACKEND] Fix mixed types MFMA fp8 instruction selection ...
• b4e20bb release/3.7.x (#9965)
• 98a34c5 [release/3.7.x] [AMD] CanonicalizePointers: Handle different base pointers an...
• 3a64615 [release/3.7.x] Enable TRITON_EXT_ENABLED for Wheels Build (#9935) (#9959)
• 74d1847 [release/3.7.x][AMD] Fix BlockPingpong for non-MFMA dot (#9618) (#9948)
• Additional commits viewable in compare view

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.