GPU Development
24 shown on page 1
Julia's_OpenClaw_Token_Optimizer
Automation skill for Julia's OpenClaw Token Optimizer.
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Julia's_OpenClaw_Token_Optimizertilegym-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 …
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-adding-cutile-kerneltilegym-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 …
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-converting-cutile-to-juliatilegym-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-onc…
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-cutile-autotuningtilegym-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.
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-cutile-pythontilegym-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…
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-improve-cutile-kernel-perftilegym-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 integra…
quarantinedClawHub- Registry
- ClawHub
- Category
- Gpu Development· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__tilegym-monkey-patch-kernels-to-transformerstilegym-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 …
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-adding-cutile-kerneltilegym-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 …
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-converting-cutile-to-juliatilegym-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 du…
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-converting-cutile-to-tritontilegym-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-onc…
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-cutile-autotuningtilegym-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.
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-cutile-pythontilegym-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…
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-improve-cutile-kernel-perftilegym-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 integra…
quarantinedNVIDIA- Registry
- NVIDIA
- Category
- GPU Development
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tilegym-monkey-patch-kernels-to-transformersjulia
Indexed by skills.sh from mindrally/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- mindrally
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__juliakernel-exploitation
Indexed by skills.sh from yaklang/hack-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- yaklang
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__kernel-exploitationtilegym-adding-cutile-kernel
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-adding-cutile-kerneltilegym-converting-cutile-to-julia
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-converting-cutile-to-juliatilegym-converting-cutile-to-triton
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-converting-cutile-to-tritontilegym-cutile-autotuning
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-cutile-autotuningtilegym-cutile-python
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-cutile-pythontilegym-improve-cutile-kernel-perf
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-improve-cutile-kernel-perftilegym-monkey-patch-kernels-to-transformers
Indexed by skills.sh from nvidia/skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- nvidia
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilegym-monkey-patch-kernels-to-transformerstilekernels-gpu-kernels
Indexed by skills.sh from aradotso/trending-skills
quarantinedskills.sh- Registry
- skills.sh
- Category
- Gpu Development· inferred
- Version
- 1.0.0
- Author
- aradotso
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__tilekernels-gpu-kernels