Skip to content

runner ade07ba: segfault (SIGSEGV) at model load when the container has zero GPU devices mapped — crashes before HTTP binds #1936

Description

@thinmintdev

Found during #1925 validation on ct151 (evidence: #1925 (comment)).

Standalone llama-server from ghcr.io/hal0ai/hal0-rocmfpx:ade07ba with no devices mapped segfaults at model load (exit 139), reproduced 2/2, before the HTTP port binds. Model: hal0-brain-sft-q8-rocmfpx.

Distinct from #1888 (silent garbage with green health): this is crash-on-load. Population: any container/LXC deployment with neither /dev/kfd nor a render node visible — post-#1923 the preflight derives such boxes to CPU slots, so exposure is narrowed to configs that explicitly pin a GPU device on a device-less box, but the runner should fail with a diagnostic, not SIGSEGV.

Note for triage: the same session confirmed renderD128-without-kfd (AMD RADV lane) reproduces #1888's empty-content garbage exactly — no new evidence there, and #1923's preflight now blocks that config.

Refs #1925, #1888.

Metadata

Metadata

Assignees

No one assigned

    Labels

    needs-triageMaintainer needs to evaluate

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions