Add new operators to MNN through a staged workflow covering data definitions, output shapes, computation, and tests. It prioritizes combining existing operators, with CPU implementations and additional hardware backends used when needed.
- Adding a new operator to MNN
- Implementing output shape calculations
- Combining existing operators for new operations
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026
Find the right workflow for MNN CPU work, from investigating slow execution to implementing calculation routines and planning tests. Compare ARM, x86_64, and RISC-V backend structures before choosing the relevant guidance.
- Choosing where to start an MNN CPU performance investigation
- Finding guidance for CPU kernel implementation
- Comparing ARM, x86_64, and RISC-V backend structures
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026
Develop or port CPU kernels, the low-level calculation routines used by MNN. Follow staged implementation guidance, check data layout agreements, register functions, and verify correctness across processor instruction sets and numerical precision settings.
- Implementing or porting an MNN CPU kernel
- Adding support for a processor instruction set
- Changing packed data layouts or tile sizes
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026
Find why MNN CPU inference is slow by examining threads, scheduling, memory layout, and the processor instruction path actually used. Operator-level measurements and comparisons with other inference frameworks help identify which layer needs improvement across ARM, x86_64, and RISC-V.
- Investigate slow CPU operators or LLM inference
- Diagnose thread count and memory usage anomalies
- Locate the cause of a performance regression
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026
Optimize and troubleshoot MNN's Hexagon DSP backend, which runs computation on a dedicated processor. The workflow uses device measurements to identify bottlenecks, compare v79 and v81 architectures, verify correctness, and investigate crashes or memory usage.
- Finding bottlenecks in Hexagon operators
- Checking changes on v79 and v81 devices
- Investigating cDSP crashes and device disconnects
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026
Guide MNN Metal backend development and optimization, from finding performance bottlenecks to changing GPU computation, combining operators, and adjusting execution scheduling. A task-based document index directs work toward relevant implementation rules, benchmarks, and correctness checks.
- Finding bottlenecks in Metal inference
- Adding or modifying Metal kernels
- Combining operators into one GPU dispatch
alibaba/MNN☆ 16.2KUpdated Oct 16, 2026