10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 521 ms

1. 1tilegym-converting-cutile-to-tritonverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-converting-cutile-to-triton

     Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags

2. 2tilegym-converting-cutile-to-juliaverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-converting-cutile-to-julia

     Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or

3. 3tilegym-cutile-pythonverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-cutile-python

     Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

4. 4tilegym-adding-cutile-kernelverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-adding-cutile-kernel

     Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to regi

5. 5tilegym-improve-cutile-kernel-perfverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-improve-cutile-kernel-perf

     Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimiz

6. 6tilegym-cutile-autotuningverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-cutile-autotuning

     Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern,

7. 7tilegym-monkey-patch-kernels-to-transformersverified and signedpassport

   skillnvidia/skillsrecord

   • tilegym-monkey-patch-kernels-to-transformers

     Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels in

8. 8tritonverified and signedpassport

   librarytriton-lang/tritonrecord43,061,838 downloads/month

   • Compiler

   • Deep

   • Learning