Skip to content

[ET Device Support] CUDA-native Qwen 3.5 MoE inference with device tensor pipeline#18788

Open
Gasoonjia wants to merge 7 commits into
gh/gasoonjia/164/basefrom
gh/gasoonjia/164/head
Open

[ET Device Support] CUDA-native Qwen 3.5 MoE inference with device tensor pipeline#18788
Gasoonjia wants to merge 7 commits into
gh/gasoonjia/164/basefrom
gh/gasoonjia/164/head

Update

e6785b1
Select commit
Loading
Failed to load commit list.
PyTorch Bot / Dr.CI completed Jun 12, 2026 in 0s

Dr.CI classification results

{"FAILED":[{"workflowId":27405306344,"workflowUniqueId":63454257,"id":80993110173,"runnerName":"i-05ddda832cb75ec02","authorEmail":"gasoonjia@icloud.com","name":"pull / test-multimodal-linux (gemma3-4b) / linux-job","jobName":"test-multimodal-linux (gemma3-4b) / linux-job","conclusion":"failure","completed_at":"2026-06-12T09:21:04.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/27405306344/job/80993110173","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/80993110173","head_branch":"gh/gasoonjia/164/head","pr_number":18788,"head_sha":"e6785b107f4ce3f6abc7a7aa4a9b4292b5a90981","head_sha_timestamp":"2026-06-12T08:50:29.000000000Z","failure_captures":["RuntimeError: Command docker exec -t 02abc3b32a32bf514442b376355a91830ff32d1c01af35a0d5dd0b75443bb8cc /exec failed with exit code 139"],"failure_lines":["RuntimeError: Command docker exec -t 02abc3b32a32bf514442b376355a91830ff32d1c01af35a0d5dd0b75443bb8cc /exec failed with exit code 139"],"failure_context":[],"time":"2026-06-12T08:52:02.000000000Z"},{"workflowId":27405306344,"workflowUniqueId":63454257,"id":80993109726,"runnerName":"i-049f0b758122a2c3c","authorEmail":"gasoonjia@icloud.com","name":"pull / test-samsung-quantmodels-linux / linux-job","jobName":"test-samsung-quantmodels-linux / linux-job","conclusion":"failure","completed_at":"2026-06-12T09:07:38.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/27405306344/job/80993109726","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/80993109726","head_branch":"gh/gasoonjia/164/head","pr_number":18788,"head_sha":"e6785b107f4ce3f6abc7a7aa4a9b4292b5a90981","head_sha_timestamp":"2026-06-12T08:50:29.000000000Z","failure_captures":["RuntimeError: Command docker exec -t 381715f2a6151dbd5ea99067bdedc5400aa6d7d256978b1e2917ca4908c2c53f /exec failed with exit code 1"],"failure_lines":["RuntimeError: Command docker exec -t 381715f2a6151dbd5ea99067bdedc5400aa6d7d256978b1e2917ca4908c2c53f /exec failed with exit code 1"],"failure_context":[],"time":"2026-06-12T08:52:02.000000000Z"},{"workflowId":27405309914,"workflowUniqueId":216132948,"id":80997940606,"runnerName":"i-08abd909784e08249","authorEmail":"gasoonjia@icloud.com","name":"Test CUDA Windows Export and E2E / test-model-cuda-windows-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / windows-job","jobName":"test-model-cuda-windows-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / windows-job","conclusion":"failure","completed_at":"2026-06-12T10:01:04.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/27405309914/job/80997940606","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/80997940606","head_branch":"ciflow/cuda/18788","pr_number":18788,"head_sha":"e6785b107f4ce3f6abc7a7aa4a9b4292b5a90981","head_sha_timestamp":"2026-06-12T08:50:29.000000000Z","failure_captures":["Process completed with exit code 1."],"failure_lines":["##[error]Process completed with exit code 1."],"failure_context":[],"time":"2026-06-12T09:21:49.000000000Z"}],"FLAKY":[{"workflowId":27405306350,"workflowUniqueId":198852395,"id":80996352473,"runnerName":"i-0525ab7de4f8e9881","authorEmail":"gasoonjia@icloud.com","name":"Test Metal Backend / test-model-metal-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job","jobName":"test-model-metal-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job","conclusion":"failure","completed_at":"2026-06-12T09:20:15.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/27405306350/job/80996352473","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/80996352473","head_branch":"gh/gasoonjia/164/head","pr_number":18788,"head_sha":"e6785b107f4ce3f6abc7a7aa4a9b4292b5a90981","head_sha_timestamp":"2026-06-12T08:50:29.000000000Z","failure_captures":[],"failure_lines":[],"failure_context":[],"time":"2026-06-12T09:11:59.000000000Z"}],"BROKEN_TRUNK":[],"UNSTABLE":[],"UNKNOWN":[{"workflowId":27405309822,"workflowUniqueId":195669493,"id":80992979986,"runnerName":"i-01725c0b91bc33cde","authorEmail":"gasoonjia@icloud.com","name":"Test CUDA Builds / unittest-cuda / linux-job","jobName":"unittest-cuda / linux-job","conclusion":"failure","completed_at":"2026-06-12T09:38:46.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/27405309822/job/80992979986","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/80992979986","head_branch":"ciflow/cuda/18788","pr_number":18788,"head_sha":"e6785b107f4ce3f6abc7a7aa4a9b4292b5a90981","head_sha_timestamp":"2026-06-12T08:50:29.000000000Z","failure_captures":["examples/models/qwen3_5_moe/test_sampler.py::TestSampler::test_output_shape_and_dtype"],"failure_lines":["FAILED examples/models/qwen3_5_moe/test_sampler.py::TestSampler::test_output_shape_and_dtype - AssertionError: torch.int64 != torch.float32"],"failure_context":[],"time":"2026-06-12T08:51:15.000000000Z"}],"AWAITING_APPROVAL":[]}