Tilegym cutile python vs Tilegym improve cutile kernel perf
Tilegym cutile python is an open-source agent skill for developer tools. Tilegym improve cutile kernel perf is an open-source agent skill for developer tools.
- Tilegym cutile python is best for write a relu or softmax kernel for a given tensor shape.
- Tilegym improve cutile kernel perf is best for speed up a slow cutile attention or matmul kernel in tilegym.
- What it is
- Tilegym cutile python is an open-source agent skill for developer tools.Tilegym improve cutile kernel perf is an open-source agent skill for developer tools.
- Best for
- Write a ReLU or softmax kernel for a given tensor shapeSpeed up a slow cuTile attention or matmul kernel in TileGym
- Kind
- SkillSkill
- Pricing
- Open sourceOpen source
- Platforms
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, GooseClaude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- GitHub stars
- 4K4K
- Last commit
- Nov 2026Nov 2026
- License
- Apache-2.0Apache-2.0
- Open source
- Good for
- Write a ReLU or softmax kernel for a given tensor shape; Convert a PyTorch matmul or attention block into a cuTile implementation; Debug a cuTile kernel that fails to compile or produces wrong numbersSpeed up a slow cuTile attention or matmul kernel in TileGym; Tune autotune configs for a cuTile kernel on a Blackwell GPU; Benchmark and refine a cuTile kernel over several iterations
What Tilegym cutile python does
Kernel writing workflow
Step-by-step guidance for designing, typing, implementing and launching a single cuTile kernel.
Example and TileGym search
Directs the agent to check TileGym ops and packaged examples before writing new code.
Mandatory run-and-validate loop
Requires generated code to be executed and compared against a reference, with retries on failure.
Multi-kernel orchestration
Routes complex multi-operation tasks to a sub-agent pipeline with analyzer, kernel and composer stages.
Code generation rules
Enforces typed constants, power-of-two tile sizes, tile indices and a pure cuTile forward path.
Clarifying tradeoffs
Prompts the agent to present options before optimizing for speed, precision or architecture changes.
What Tilegym improve cutile kernel perf does
Setup and baseline capture
Creates a branch, locates the cuTile kernel and launch wrapper, and records baseline latency.
Bottleneck classification
Sorts kernels into memory-bound, balanced or compute-bound using arithmetic intensity to set priorities.
One-change experiment loop
Applies a single optimization per iteration, verifies correctness, and re-benchmarks before deciding.
Tunable parameter catalog
Reference covering tile sizes, occupancy, TMA, persistent scheduling, num_ctas and latency hints.
IR dump analysis
Guides inspecting compiled cuTile IR to compare variants and diagnose errors.
Progress tracking table
Logs each iteration's latency, correctness result and keep or revert status in a Markdown table.
Tilegym cutile python vs Tilegym improve cutile kernel perf: questions
Is Tilegym cutile python or Tilegym improve cutile kernel perf cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between Tilegym cutile python and Tilegym improve cutile kernel perf?
Tilegym cutile python is an open-source agent skill for developer tools. Tilegym improve cutile kernel perf is an open-source agent skill for developer tools.
