Compiler parameters influence the way the prediction subroutine is generated from a tree ensemble model.
name of model annotation file. Use the class
treelite.Annotatorto generate this file.
whether to quantize threshold points (0: no, >0: yes)
option to enable parallel compilation; if set to nonzero, the trees will be evely distributed into
[parallel_comp]files. Set this option to improve compilation time and reduce memory consumption during compilation.
if >0, produce extra messages
native lib name (without extension)
parameter for folding rarely visited subtrees (no if/else blocks); all nodes whose data counts are lower than that of the root node of the decision tree by [code_folding_req] will be folded. To diable folding, set to +inf. If hessian sums are available, they will be used as proxies of data counts.
Only applicable when compiler is set to
failsafe. If set to a positive value, the fail-safe compiler will not emit large constant arrays to the C code. Instead, the arrays will be emitted as an ELF binary (Linux only). For large arrays, it is much faster to directly dump ELF binaries than to pass them to a C compiler.