code wiki / (root) / nx_gguf_load_model.nx

nx_gguf_load_model.nx

buildroot/runtime/nx_gguf_load_model.nx

6212 B147 linesdepth 6pulls 8 transitivereach 20 importersview sourcekind librarytopic gguf
docsdependenciesstructsconstsfunctions

about

nx_gguf_load_model.nx -- top-level model-tensor loader. L4 brick: the missing companion to nx_gguf_load_block.nx. Where block_load reads the 9 per-layer tensors, this brick reads the 3 top-level (non-per-layer) tensors a Llama-class GGUF carries: token_embd.weight -- vocab x hidden (embedding table) output.weight -- hidden x vocab (output projection / "lm head"; often tied to token_embd) output_norm.weight -- hidden (final RMSNorm scale) Together with nx_gguf_load_block, this brick covers the FULL set of tensor names a Llama-2 / Llama-3 / Mistral / Qwen GGUF contains (modulo extra K/V biases that don't appear in standard files). After this brick, the path from text prompt -> first emitted token is loader-complete; the next workstream is `nx_llm_run` v2 which composes load_model + load_block + transformer_block_forward + final_norm + output_projection + softmax + sample. Bits-up composition: nx_gguf.nx, nx_gguf_load.nx -- header + per-tensor load nx_tensor.nx -- NxTensor output genealogy_id: llama_gguf_naming_gerganov_2024 + standard_lm_head lineage_id: substrate_gguf_model_loader_v1

dependencies 5 imports · 2 importers

nx_syscalls.nx nx_tier.nx nx_tensor.nx nx_gguf.nx nx_gguf_load.nx nx_gguf_load_model.nx nx_gguf_load_model_test.nx nx_llm_run_v2.nx

imports: nx_syscalls.nxnx_tier.nxnx_tensor.nxnx_gguf.nxnx_gguf_load.nx

imported by: nx_gguf_load_model_test.nxnx_llm_run_v2.nx

structs

80struct NxGgufModelWeights

consts

54const NX_GML_OK: nx_int = 0
55const NX_GML_ERR_EMBED_NOT_FOUND: nx_int = 1
56const NX_GML_ERR_OUTPUT_NOT_FOUND: nx_int = 2
57const NX_GML_ERR_NORM_NOT_FOUND: nx_int = 3
58const NX_GML_ERR_LOAD_FAIL: nx_int = 4
59const NX_GML_N_VERDICTS: nx_int = 5
88const NX_GML_BUNDLE_BYTES: nx_int = 32 // 4 fields * 8

functions

61func nx_gml_verdict_is_valid(v: nx_int) -> nx_int
called by 1: main
92func nx_gguf_load_model_weights(buf: *u8, hdr: *NxGgufHeader,