nx_f32_llm_run_test.nx
buildroot/runtime/nx_f32_llm_run_test.nx
about
nx_f32_llm_run_test.nx -- smoke for nx_f32_llm_run.nx.
Composes tiny-Llama fixture + run loop. Zero-weight fixture
means argmax always returns 0 ('a' = byte 0x61). Verifies the
runner generates max_new_tokens bytes of 'a's.
dependencies 13 imports · 0 importers
diagram shows first 10 each side; +3 more imports, +0 more importers in the complete lists below.
imports: nx_syscalls.nxnx_tier.nxnx_bpe.nxnx_gguf.nxnx_gguf_fixture_tiny.nxnx_f32_kv_cache.nxnx_f32_llama_block.nxnx_f32_llama_stack.nxnx_f32_llama_layer_load.nxnx_f32_llm.nxnx_f32_llm_load.nxnx_f32_sampler.nxnx_f32_llm_run.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
| 21 | func main() -> i64 |