Links the local llama.cpp April build (libmtmd exports clip_* internals); generates deterministic PPM test images; dumps preprocessed f32 tensor and projected [n_tokens x 4096] embeddings. Reference stats recorded: radar 512x384 -> 192 tokens, cpu-vs-metal spread ~2e-4 abs on embd values. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
39 KiB
Executable file
39 KiB
Executable file