rob thijssen
abc6e605b8
Some checks failed
CI / CUDA type-check (push) Failing after 19s
build-prerelease / Resolve version stamps (push) Successful in 43s
CI / Format (push) Successful in 50s
CI / Clippy (push) Failing after 57s
build-prerelease / Build neuron-ada (push) Failing after 48s
build-prerelease / Build cortex binary (push) Successful in 5m5s
build-prerelease / Build neuron-blackwell (push) Successful in 6m38s
build-prerelease / Package cortex RPM (push) Successful in 1m27s
build-prerelease / Build neuron-ampere (push) Successful in 7m27s
build-prerelease / Package helexa-neuron-ada RPM (push) Has been skipped
build-prerelease / Package helexa-neuron-ampere RPM (push) Has been skipped
build-prerelease / Package helexa-neuron-blackwell RPM (push) Has been skipped
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been skipped
CI / Test (push) Successful in 10m27s
CI / Build cortex SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
One-shot, env-gated fault injector for beast verification: when NEURON_DEBUG_POISON names a model, the first request for it triggers the auto-recovery path as if a device fault had occurred — exercising unload→reload→healthy without corrupting the GPU. Latched so it fires exactly once (no recovery loop). No-op unless the env var is set; wired into both the single-GPU and TP chat poison gates. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>