nx_f32_llm_load_test.nx
buildroot/runtime/nx_f32_llm_load_test.nx
about
nx_f32_llm_load_test.nx -- smoke for nx_f32_llm_load.nx.
Uses the tiny-Llama fixture (1 layer, F32 zero weights) to verify
the model-level binder populates embed + gamma_out + lm_head + 1
layer correctly. Then composes with nx_f32_llm_forward to verify
the loaded model can run a forward pass.
dependencies 11 imports · 0 importers
diagram shows first 10 each side; +1 more imports, +0 more importers in the complete lists below.
imports: nx_syscalls.nxnx_tier.nxnx_gguf.nxnx_gguf_fixture_tiny.nxnx_gguf_load_f32.nxnx_f32_kv_cache.nxnx_f32_llama_block.nxnx_f32_llama_stack.nxnx_f32_llama_layer_load.nxnx_f32_llm.nxnx_f32_llm_load.nx
imported by: nobody (leaf or entry point)
call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown
structs
| none |
consts
| none |
functions
| 20 | func main() -> i64 |