rob thijssen
98d095099a
All checks were successful
CI / Format (push) Successful in 8s
CI / Clippy (push) Successful in 2m20s
CI / Test (push) Successful in 6m15s
CI / CUDA type-check (push) Successful in 12m40s
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
CI / Format (pull_request) Successful in 8s
CI / Clippy (pull_request) Successful in 2m18s
CI / Test (pull_request) Successful in 5m37s
CI / CUDA type-check (pull_request) Successful in 12m41s
CI / Build cortex SRPM (pull_request) Has been skipped
CI / Publish cortex to COPR (pull_request) Has been skipped
CI / Build neuron SRPM (pull_request) Has been skipped
CI / Publish neuron to COPR (pull_request) Has been skipped
CI / Bump version in source (pull_request) Has been skipped
- derive_limit now logs every input and intermediate term (free VRAM, prefill rate, vram/throughput ceilings, hard clamp, result) at DEBUG so a surprising advertised limit is diagnosable from the journal — needed right now: beast's 27B advertises context=0 post-reboot and no by-hand input combination reproduces it. - profile_from_qwen3_5_config had the same too-narrow model_type gate as #124 and a plain serde parse that rejects the flat qwen3_next layout — Coder-Next has never had an advertised limit or the #65 length-aware preflight. Parse via Config::from_config_json and accept both types. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TczcGF7JSjJs8r15RSSGpx