rob thijssen
18ae3c30ee
All checks were successful
CI / Format (push) Successful in 34s
build-prerelease / Resolve version stamps (push) Successful in 35s
CI / Clippy (push) Successful in 2m17s
CI / Test (push) Successful in 4m16s
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
build-prerelease / Build cortex binary (push) Successful in 4m28s
build-prerelease / Build neuron-blackwell (push) Successful in 3m42s
build-prerelease / Package cortex RPM (push) Successful in 1m25s
build-prerelease / Build neuron-ampere (push) Successful in 4m27s
build-prerelease / Build neuron-ada (push) Successful in 4m51s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m50s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m40s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 6m52s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 2m32s
Two followups from the live single-GPU validation pass. 1. deploy.sh now ensures libcudnn.so.9 is available on each neuron host before installing/upgrading the package. Probes ldconfig first so hosts with a manual (tar/runfile) cuDNN install are untouched, then adds NVIDIA's RHEL9 CUDA repo (the Fedora 43 CUDA repo doesn't ship cuDNN; only the RHEL9 one does) and installs libcudnn9-cuda-13. benjy hit "cannot open shared object file: libcudnn.so.9" during validation; this prevents that recurring. 2. candle.rs applies a 1.1 repetition penalty over the last 64 generated tokens before sampling, in both the non-streaming chat_completion path and the streaming chat_completion_stream path. Without it small Q4_K_M models degenerate into "Wait, no, no..." loops once they hit a confident-but-wrong path; with it sampling stays coherent. Defaults match mistral.rs and llama.cpp; exposing the value via the OpenAI request (frequency/presence penalty mapping) is Stage 8 territory. Both routes through a new sample_with_penalty() helper so future sampling tweaks land in one place. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>