vh
f21369e4ac
torch keeps CUDA state per host thread (cuBLAS handles and workspaces), partly outside the per-process VRAM cap. Scoring on anyio's threadpool let 40 threads each create it: measured on fv-ml1 GPU 3, +252 MiB outside the cap and +326 MiB inside, which pushed the process past the 10,300 MiB GPU 1 budget. Load, warm-up and every call now run on the same single thread.