Ilker ManapandClaude Opus 5.5 dc483d8c68 Choose each engine's build from the node's hardware, for every GPU generation ...

Each engine has a list of builds, best first, from what its project
publishes and how each was compiled: llama.cpp CUDA 13.3, CUDA 12.8
(driver 570 for the GPUs it ships as PTX), then Vulkan, never the CPU
build on an NVIDIA node; vLLM CUDA 13, then CUDA 12.9, and for GPUs
older than every build of the version asked for, the newest built for
them (V100: 0.19.1). The node takes the first its hardware meets and
that installs and computes on the GPU, moving on when one does not, and
reports the version it runs. GPU processes are read from nvidia-smi's
full report, so Vulkan engines count as on their GPU.

Refs #2.

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

2026-10-01 14:35:58 +02:00

..

install_test.go

Choose each engine's build from the node's hardware, for every GPU generation

2026-10-01 14:35:58 +02:00

install.go

Choose each engine's build from the node's hardware, for every GPU generation

2026-10-01 14:35:58 +02:00

python_test.go

Choose each engine's build from the node's hardware, for every GPU generation

2026-10-01 14:35:58 +02:00

python.go

Choose each engine's build from the node's hardware, for every GPU generation

2026-10-01 14:35:58 +02:00

recipe.go

Choose each engine's build from the node's hardware, for every GPU generation

2026-10-01 14:35:58 +02:00