Ilker ManapandClaude Opus 5.5 057be16a92 Do not call a GPU shard ready while it computes on the CPU ...

llama.cpp whose CUDA backend cannot load runs on the CPU without an
error. The CUDA build is now asked for its devices when installed, a
shard on GPUs must hold memory on each before it is ready, and
engine-check reports the devices. Shards get CUDA_DEVICE_ORDER=PCI_BUS_ID
so CUDA numbers GPUs as placement does.

Refs #2 (item 2).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-01 11:54:39 +02:00

..

install_test.go

Do not call a GPU shard ready while it computes on the CPU

2026-10-01 11:54:39 +02:00

install.go

Do not call a GPU shard ready while it computes on the CPU

2026-10-01 11:54:39 +02:00

python_test.go

Install vLLM on every GPU node that can run it, as llama.cpp is

2026-09-29 13:15:54 +02:00

python.go

Install vLLM on every GPU node that can run it, as llama.cpp is

2026-09-29 13:15:54 +02:00

recipe.go

Do not call a GPU shard ready while it computes on the CPU

2026-10-01 11:54:39 +02:00