Files
cortex/crates
rob thijssen f05882369d
All checks were successful
build-prerelease / Resolve version stamps (push) Successful in 33s
CI / Format (push) Successful in 34s
CI / Clippy (push) Successful in 2m18s
build-prerelease / Build cortex binary (push) Successful in 4m28s
build-prerelease / Package cortex RPM (push) Successful in 1m28s
build-prerelease / Build neuron-ampere (push) Successful in 8m25s
build-prerelease / Build neuron-ada (push) Successful in 8m54s
CI / Test (push) Successful in 4m43s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Build neuron-blackwell (push) Successful in 3m51s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m55s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 2m54s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m43s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 1m5s
fix(neuron): don't poison the model on tokio JoinError panics
CUDA driver failures propagate as Err through `?` and become
`Ok(Err(InferenceError::Other(_)))` from the spawned task — those are
real device faults and still poison the model. Tokio JoinError is
different: it fires on Rust-level panic (tokenizer bug, sampler bug,
serialisation, the UTF-8 slice that landed in commit bd04d7f before
the fix) or task cancellation. Those don't touch the device context,
so failing the one request without tearing down the model is correct.

Two sites changed:

  - chat_completion's CPU spawn_blocking handler — JoinError no longer
    sets loaded.poisoned.
  - chat_completion_tp's tokio::spawn wrapper — JoinError no longer
    sets tp_for_marker.poisoned. The inner-Err case still does.

Each path logs the cause (panicked / was cancelled / ended abnormally)
explicitly so the journal makes the new behaviour obvious — search for
"model NOT marked poisoned" to find these events.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 18:02:52 +03:00
..