vllm-project/vllm · error · ValueError

chrome_trace output requires proton_data='trace'

Error message

chrome_trace output requires proton_data='trace'

What it means

ProfilerConfig enforces consistency between proton_output_format and proton_data when profiler='proton'. chrome_trace output requires the 'trace' data mode, because a Chrome trace can only be produced from trace-style records, not from the hierarchical tree data.

Source

Thrown at vllm/config/profiler.py:224

            options = ", ".join(non_default_proton_options)
            raise ValueError(
                f"{options} only applicable when profiler is set to 'proton'"
            )
        if self.profiler == "proton" and not proton_profiler_dir:
            raise ValueError(
                "proton_profiler_dir must be set when profiler is 'proton'"
            )
        if proton_profiler_dir:
            if _is_uri_path(proton_profiler_dir):
                raise ValueError("proton_profiler_dir must be a local directory")
            self.proton_profiler_dir = os.path.abspath(
                os.path.expanduser(proton_profiler_dir)
            )

        if self.profiler == "proton":
            output_format = self.proton_output_format
            if output_format == "chrome_trace" and self.proton_data != "trace":
                raise ValueError("chrome_trace output requires proton_data='trace'")
            if (
                output_format in ("hatchet", "hatchet_msgpack")
                and self.proton_data != "tree"
            ):
                raise ValueError(f"{output_format} output requires proton_data='tree'")

        if self.capture_torch_profiler and self.profiler != "torch":
            raise ValueError(
                "capture_torch_profiler is only applicable when profiler is "
                "set to 'torch'"
            )

        return self

View on GitHub (pinned to c794754062)

Solutions

1. Set proton_data='trace' together with proton_output_format='chrome_trace'.
2. Or keep proton_data='tree' and use a hatchet output format instead.

Example fix

# before
ProfilerConfig(profiler='proton', proton_profiler_dir='/tmp/p', proton_output_format='chrome_trace')

# after
ProfilerConfig(profiler='proton', proton_profiler_dir='/tmp/p', proton_data='trace', proton_output_format='chrome_trace')

def validate_proton_output(data: str, fmt: str | None) -> None:
    if fmt == "chrome_trace" and data != "trace":
        raise SystemExit("proton_output_format='chrome_trace' requires proton_data='trace'")

When it happens

Trigger: Passing --profiler-config profiler=proton,proton_output_format=chrome_trace with proton_data left at its default 'tree' (or explicitly 'tree').

Common situations: Users wanting Chrome-trace output without realizing the data mode must change to 'trace'; copying output-format options from a profiling script that assumed trace data.

Related errors

• {options} only applicable when profiler is set to 'proton'
• proton_profiler_dir must be set when profiler is 'proton'
• proton_profiler_dir must be a local directory
• {output_format} output requires proton_data='tree'
• Unable to use nsight profiling unless workers run with Ray.

AI-assisted analysis of vllm-project/vllm@c794754062 (2026-08-14). Data as JSON: /api/errors/6a78626076a1c126. Report an issue: GitHub.