code wiki / (root) / nx_coder_swap_gate.nx

nx_coder_swap_gate.nx

buildroot/runtime/nx_coder_swap_gate.nx

6262 B156 linesdepth 8pulls 17 transitivereach 0 importersview sourcekind gate/prooftopic coder
docsdependenciesstructsconstsfunctions

about

nx_coder_swap_gate.nx -- L3 gate: the Qwen2.5-Coder-0.5B q8_0 GGUF staged ADDITIVELY at /home/elderwesto/nx_stage/nx_coder_model.gguf must be REAL and LOADABLE through the SAME sovereign stack before any capability claim (dossier row L3). Teeth: T1 GGUF parses (nx_gguf_parse OK on the full file) T2 named-tensor load+dequant works (blk.0.attn_q.weight -> Q16, >0 values) = the exact pipeline the serve uses, on the CODER file's own quant layout T3 FIM special tokens present in tokenizer metadata (<|fim_prefix|> searched in the head) T4 identity: the metadata head names "coder" (proves this is the Coder file, not a base copy) T5 NEG corrupted-magic head must FAIL the parser (liar-kill: the parser really validates) license_tier: ORIGINAL expect_exit: 0

dependencies 8 imports · 0 importers

nx_syscalls.nx nx_tier.nx nx_le.nx nx_tensor.nx nx_gguf.nx nx_gguf_load.nx nx_nofloat_llm.nx nx_gate_verdict.nx nx_coder_swap_gate.nx

imports: nx_syscalls.nxnx_tier.nxnx_le.nxnx_tensor.nxnx_gguf.nxnx_gguf_load.nxnx_nofloat_llm.nxnx_gate_verdict.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 cs_puts sys_write cs_num sys_mmap ↻ sys_write ↻ 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 ↻ cs_slen load_named_q16 nx_gguf_find_tensor nx_gguf_tensor_at nx_gguf_name_equals nx_gguf_tensor_at ↻ nx_gguf_tensor_n_values dequant_to_q16 f32_to_q16 nx_le_read_u32 ↻ f16_to_q16 nx_le_read_u16 nx_gguf_dequant_q4_k_q14 nx_gguf_dequant_q4_k nx_le_read_u16 ↻ _gguf_f16_to_q24 nx_le_read_u8 q6k_block

structs

none

consts

none

functions

20func cs_puts(s: *u8) -> i64 { var n: i64=0; while s[n]!=(0 as u8){n=n+1} sys_write(1,s,n); return 0 }
called by 1: main calls 1: sys_write
21func cs_num(v: i64) -> i64 { let b: *u8=sys_mmap(28); var m: i64=v; if m<0{m=0-m;sys_write(1,"-" as *u8,1)} let t: *u8=sys_mmap(28); var k: i64=0; if m==0{t[0]=48 as u8;k=1} while m>0{t[k]=(48+(m%10)) as u8;m=m/10;k=k+1} var i: i64=0; while i<k{b[i]=t[k-1-i];i=i+1} sys_write(1,b,k); return 0 }
called by 1: main calls 2: sys_mmapsys_write
22func cs_slen(s: *u8) -> i64 { var n: i64=0; while s[n]!=(0 as u8){n=n+1} return n }
called by 2: cs_containsmain
25func cs_contains(hay: *u8, hn: i64, nd: *u8) -> i64
called by 1: main calls 1: cs_slen
47func main() -> i64