brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
relax-compileGuides TVM Relax IR construction/import, optimization pipelines, tvm.compile, executable export/load, and custom codegen boundaries.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when a task involves high-level TVM Relax IR, model import,
optimization pipelines, tvm.compile, VM execution, or deployable executable
artifacts.
../install-build/SKILL.md.relax.get_pipeline("zero")
is a safe baseline for tutorial-style CPU workflows; larger model and dlight
flows need backend-specific checks.tvm.compile(mod, target, relax_pipeline=..., tir_pipeline=...).relax.VirtualMachine or export/load it for a
deployment workflow.references/troubleshooting.md when the
failure is about target mismatch, optional frontend dependencies, export/load,
or pass/codegen boundaries.llvm. Run scripts/relax_compile_smoke.py
before diagnosing a larger model.../s-tir-tuning/SKILL.md.../rpc-deployment/SKILL.md for upload/load/run
and tracker/server details.The verified top-level compile entry point is:
tvm.compile(
mod,
target=None,
*,
relax_pipeline="default",
tir_pipeline="default",
)
It accepts a Relax/TIR IRModule or TIRx PrimFunc and returns a runtime
Executable. The pipeline arguments accept a named pipeline, pass object, or
callable depending on the workflow.