Function print_cli_diagnostics

ds4_help.c:244–263

    opt(fp, c, "--role ROLE", "Distributed role: coordinator or worker.");
    opt(fp, c, "--layers A:B", "Inclusive layer slice, e.g. 0:20 or 21:output.");
    opt(fp, c, "--listen HOST PORT", "Coordinator listen address; workers may use it for their data listener.");
    opt(fp, c, "--coordinator HOST PORT", "Coordinator address for --role worker.");
    opt(fp, c, "--dist-prefill-chunk N", "Coordinator prefill pipeline chunk size. Default: session cap.");
    opt(fp, c, "--dist-prefill-window N", "Max prefill chunks in flight. Default: workers+2, capped at 8.");
    opt(fp, c, "--dist-activation-bits N", "Hidden-state transport width: 32, 16, or 8. Default: 32");
    opt(fp, c, "--dist-replay-check", "Diagnostic: reset and replay prompt, then compare logits.");
    opt(fp, c, "--debug", "Print coordinator route/debug logs.");
    fputc('\n', fp);
    title(fp, c, "Tensor Parallelism");
    fputc('\n', fp);
    para(fp, c, "Tensor parallelism uses the same coordinator/worker addresses as distributed mode, but always runs one 50/50 worker. Add --tensor-parallel, omit --layers, start the worker, then start the coordinator.");
    fputc('\n', fp);
    opt(fp, c, "--tensor-parallel", "Switch --role/--listen/--coordinator to two-machine tensor parallelism.");
    opt(fp, c, "--transport auto|rdma|tcp", "Tensor gate transport. Default: auto");
    opt(fp, c, "--rdma-device NAME", "Select a verbs device when auto-detection is ambiguous.");
    opt(fp, c, "--rdma-gid-index N", "Select the local verbs GID index.");
    opt(fp, c, "--tensor-parallel-token-prefill", "GLM diagnostic: prefill one token at a time for exact arithmetic.");
    opt(fp, c, "--debug-hash N", "Cross-check hidden state every N tokens.");
    fputc('\n', fp);
}

static void print_cli_diagnostics(FILE *fp, const help_colors *c);