Opt Merge Multi Launch Kernels

Procedural recipe for fusing multiple `air.launch` kernels into one multi-launch ELF (single XRT invocation). Invoked by phase-4-prefill-optimization and phase-5-decode-optimization to fuse kernel groups when building NEW model-specific fused ELFs (kernel-first path). Reduces XRT dispatch overhead (~50–200 µs per call on NPU2).

xilinx Updated 157 repo stars

File contents

xilinx/mlir-air commit fb43f65aee

Frequently asked questions

npx get-skill add xilinx/opt-merge-multi-launch-kernels