Test CUDA Windows Export and E2E

[MLX] Add off-graph KV cache ring runtime (#21532) #140

Sign in to view logs

Triggered via push August 4, 2026 19:45

main

Status Cancelled

Total duration 1d 0h 0m 43s

Artifacts –

cuda-windows.yml

on: push

Get changed files / get-changed-files

CI run decision / decide

Matrix: export-model-cuda-windows-artifact

Matrix: test-model-cuda-windows-e2e

Waiting for pending jobs

Annotations

6 errors and 1 warning

export-model-cuda-windows-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile... / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

export-model-cuda-windows-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

export-model-cuda-windows-artifact (nvidia, parakeet-tdt, quantized-int4-weight-only) / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

export-model-cuda-windows-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job

The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s

CI run decision / decide

Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@v4. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/