code wiki / (root) / nx_f32_llm_live_dims_test.nx

nx_f32_llm_live_dims_test.nx

buildroot/runtime/nx_f32_llm_live_dims_test.nx

2421 B62 linesdepth 12pulls 28 transitivereach 0 importersview sourcekind gate/prooftopic f32
docsdependenciesstructsconstsfunctions

about

nx_f32_llm_live_dims_test.nx -- LIVE FIRE on the real Qwen2.5-0.5B-Instruct. Reads /tmp/nx_real_model.gguf (~491 MB, Apache 2.0) and verifies nx_f32_llm_read_dims_from_gguf correctly derives Qwen2.5-0.5B-Instruct dimensions from the real GGUF metadata. Expected dims (from Qwen2.5-0.5B-Instruct config.json, public): n_layers = 24 hidden_dim = 896 n_heads = 14 n_kv_heads = 2 (GQA: 7x grouping) head_dim = 64 (hidden_dim / n_heads = 896 / 14 = 64) ffn_dim = 4864 vocab_size = 151936

dependencies 7 imports · 0 importers

nx_syscalls.nx nx_tier.nx nx_gguf.nx nx_gguf_load.nx nx_gguf_meta.nx nx_f32_llm.nx nx_f32_llm_read_dims.nx nx_f32_llm_live_dims_test.nx

imports: nx_syscalls.nxnx_tier.nxnx_gguf.nxnx_gguf_load.nxnx_gguf_meta.nxnx_f32_llm.nxnx_f32_llm_read_dims.nx

imported by: nobody (leaf or entry point)

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

main sys_mmap sys_read_file sys_openat_rd sys_lseek sys_mmap ↻ sys_read sys_close 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_f32_llama_model_alloc sys_mmap ↻ nx_f32_llm_read_dims_from_ sys_mmap ↻ nx_gguf_meta_find nx_le_read_u64 ↻ nx_le_read_u32 ↻ _gmeta_bytes_equal nx_gguf_skip_value _gguf_skip_value ↻ nx_gguf_meta_read_string_l nx_le_read_u64 ↻ nx_gguf_meta_read_string_p _fld_read_arch_u32 sys_mmap ↻ _fld_concat_key nx_gguf_meta_find ↻ nx_gguf_meta_read_u32 nx_le_read_u32 ↻ _fld_read_vocab_size_from_ sys_mmap ↻ nx_gguf_find_tensor nx_gguf_tensor_at

structs

none

consts

none

functions

24func main() -> i64
calls 5: sys_mmapsys_read_filenx_gguf_parsenx_f32_llama_model_allocnx_f32_llm_read_dims_from_gguf