rob thijssen
89d98d1fb2
All checks were successful
build-prerelease / Resolve version stamps (push) Successful in 30s
CI / Format (push) Successful in 33s
CI / Clippy (push) Successful in 2m14s
build-prerelease / Build neuron-blackwell (push) Successful in 3m59s
CI / Test (push) Successful in 4m58s
build-prerelease / Build cortex binary (push) Successful in 4m36s
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 / Package cortex RPM (push) Successful in 1m26s
build-prerelease / Build neuron-ampere (push) Successful in 4m52s
build-prerelease / Build neuron-ada (push) Successful in 5m11s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m56s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 3m1s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m52s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 1m0s
Wraps each TpQwen3_5DecoderLayer::load in a with_context that captures free/total VRAM on failure, plus an info-level log after every layer that succeeds. Uses cudarc::driver::result::mem_get_info — same API mistralrs uses. Diagnostic only: forward path is unchanged. Helps distinguish true VRAM exhaustion from allocator fragmentation when loading large models at BF16 on 2x consumer GPUs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>