Compiler parameters influence the way the prediction subroutine is generated from a tree ensemble model.
annotate_in¶name of model annotation file. Use the class treelite.Annotator to generate this file.
quantize¶whether to quantize threshold points (0: no, >0: yes)
parallel_comp¶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.
verbose¶if >0, produce extra messages
native_lib_name¶native lib name (without extension)
code_folding_req¶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.
dump_array_as_elf¶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.