-
fix: make .runpod/tests.json hub tests pass on CUDA 13.0 (#299)
owen released this
2026-06-02 11:08:54 -04:00 Three coupled fixes verified end-to-end on a private fork
(TimPietruskyRunPod/worker-vllm v0.1.3 → both hub tests passing):-
tests.json allowedCudaVersions: 12.x → 13.0
The Dockerfile and hub.json moved to CUDA 13.0 in v2.20.0
(#288, #289), but tests.json was still pinned to 12.5–12.9, so
the test pod was scheduled on a GPU with driver < 13.0 and
container init failed at the nvidia-container-cli hook with
"unsatisfied condition: cuda>=13.0". -
requirements.txt kernels<0.15
huggingface/kernels v0.15.1 tightened LayerRepository to require
a revision or version argument
(https://github.com/huggingface/kernels/pull/544). transformers=5 still constructs LayerRepository(repo_id=..., layer_name=...)
without either, so worker import raised ValueError during
from transformers import .... 0.14.1 is the last safe release. -
tests.json timeout 30000 → 300000
vLLM cold start (torch.compile + FlashInfer warmup) on RTX 4090
for SmolLM2-135M takes ~60–70s before the first request can be
served. The previous 30s per-test timeout fired before the
worker came up, producing "context cancelled or timed out:
context deadline exceeded" for every test even when the worker
was healthy. 300s gives enough headroom for cold start + the
actual inference call.
Refs: DR-1161
Downloads
-