rob thijssen
9139b07d71
All checks were successful
CI / Format (push) Successful in 7s
CI / Clippy (push) Successful in 2m18s
CI / Test (push) Successful in 5m38s
CI / CUDA type-check (push) Successful in 12m35s
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
CI / Format (pull_request) Successful in 8s
CI / Clippy (pull_request) Successful in 2m14s
CI / Test (pull_request) Successful in 6m59s
CI / CUDA type-check (pull_request) Successful in 12m35s
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
The flash-attn feature only forwarded to candle-transformers, which enables flash inside ITS models — candle_flash_attn was not nameable from neuron's own attention core (E0433 in the CUDA type-check). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TczcGF7JSjJs8r15RSSGpx
145 KiB
145 KiB