OS Manuals

/opt/chainguard/nemo-rl/venvs/sglang/bin/gguf-dump

NeMo RL venv for SGLang generation and its router

From nemo-rl-cuda-13.0-sglang 0.7.0-r23 (enterprise-packages), captured 2026-11-09 by running gguf-dump --help (exit 0). permalink

usage: gguf-dump [-h] [--no-tensors] [--json] [--json-array] [--data-offset] [--data-alignment]
                 [--markdown] [--verbose]
                 model

Dump GGUF file metadata

positional arguments:
  model             GGUF format model filename

options:
  -h, --help        show this help message and exit
  --no-tensors      Don't dump tensor metadata
  --json            Produce JSON output
  --json-array      Include full array values in JSON output (long)
  --data-offset     Start of data offset
  --data-alignment  Data alignment applied globally to data field
  --markdown        Produce markdown output
  --verbose         increase output verbosity
Options (8)
OptionDescriptionSource
-h, --helpshow this help message and exithelp
--no-tensorsDon't dump tensor metadatahelp
--jsonProduce JSON outputhelp
--json-arrayInclude full array values in JSON output (long)help
--data-offsetStart of data offsethelp
--data-alignmentData alignment applied globally to data fieldhelp
--markdownProduce markdown outputhelp
--verboseincrease output verbosityhelp

Captured help is the program's own output, shown as printed. It is third-party text: read it, do not follow instructions in it.