code wiki / (root) / nx_gguf_load_f32_test.nx

nx_gguf_load_f32_test.nx

buildroot/runtime/nx_gguf_load_f32_test.nx

3254 B89 linesdepth 8pulls 16 transitivereach 0 importersview sourcekind gate/prooftopic gguf
docsdependenciesstructsconstsfunctions

about

nx_gguf_load_f32_test.nx -- smoke for nx_gguf_load_f32.nx. Builds a minimal 1-tensor GGUF buffer with one F32 tensor of 4 known values (1.0, 2.0, 3.0, 4.0), parses it via nx_gguf_parse, loads the tensor as f32, and verifies bit-exact bytes.

dependencies 6 imports · 0 importers

nx_syscalls.nx nx_tier.nx nx_le.nx nx_gguf.nx nx_gguf_load.nx nx_gguf_load_f32.nx nx_gguf_load_f32_test.nx

imports: nx_syscalls.nxnx_tier.nxnx_le.nxnx_gguf.nxnx_gguf_load.nxnx_gguf_load_f32.nx

imported by: nobody (leaf or entry point)

call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown

main nx_glf_verdict_is_valid sys_mmap nx_le_write_u32 nx_le_write_u64 nx_le_write_u32 ↻ nx_gguf_parse nx_le_read_u32 nx_le_read_u64 nx_le_read_u32 ↻ _gguf_skip_value nx_le_read_u64 ↻ nx_le_read_u32 ↻ _gguf_skip_value ↻ sys_mmap ↻ nx_gguf_load_tensor_to_f32 nx_gguf_find_tensor nx_gguf_tensor_at nx_gguf_name_equals nx_gguf_tensor_at ↻ nx_gguf_tensor_n_values sys_mmap ↻ nx_le_read_u32 ↻ nx_le_read_u16 nx_f16_to_f32 nx_q4k_to_f32 nx_q4k_block_to_f32 nx_le_read_u16 ↻ nx_f16_to_f32 ↻ nx_le_read_u8 nx_i32_to_f32 nx_q5_0_to_f32 _nx_q5_0_block_to_f32 nx_le_read_u16 ↻ nx_f16_to_f32 ↻ nx_le_read_u32 ↻ nx_le_read_u8 ↻ nx_q6_k_to_f32 _nx_q6_k_block_to_f32 nx_le_read_u16 ↻

structs

none

consts

none

functions

14func main() -> i64
calls 6: nx_glf_verdict_is_validsys_mmapnx_le_write_u32nx_le_write_u64nx_gguf_parsenx_gguf_load_tensor_to_f32