Skip to content

Windows: verify servers with >31 blocks (mp.connection.wait 63-handle ceiling)#8

Description

@ApexDevelopment

Unverified theory left over from the debugging session: in Windows thread-mode, hivemind Runtime waits on pool pipes via multiprocessing.connection.wait, which on Windows is subject to the WaitForMultipleObjects limit (max 63 handles). A 35-block server has 35 forward + 35 backward pools + 1 merged inference pool = 71 pipes; if the runtime ever waits on all of them in one call it should raise or misbehave.

The observed 35-block startup hang turned out to be a stale hivemind wheel instead, and the theory was never tested post-fix (all validation used 17-18-block servers). Test: start a >31-block server on Windows (tiny checkpoint is fine, e.g. a 35-layer synthesized model), confirm it reaches Started and serves inference. If it fails, chunk the wait or multiplex pipes in the win32 patch.

馃 Generated with Claude Code

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions