Add Gemma 4 31B-IT model, export, and quantization framework for ExecuTorch #19213
Dr.CI classification results
{"FAILED":[{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888878,"runnerName":"i-02f0a89c84e42aaac","authorEmail":"[email protected]","name":"pull / test-lora-multimethod-linux / linux-job","jobName":"test-lora-multimethod-linux / linux-job","conclusion":"failure","completed_at":"2026-05-05T17:19:15.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888878","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888878","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["RuntimeError: Command docker exec -t 69da981df7a449f94843b13654178ee638b3613ffe9ca269e53ff10b8035caa0 /exec failed with exit code 1"],"failure_lines":["RuntimeError: Command docker exec -t 69da981df7a449f94843b13654178ee638b3613ffe9ca269e53ff10b8035caa0 /exec failed with exit code 1"],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"},{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888246,"runnerName":"i-08ec665938fb378ac","authorEmail":"[email protected]","name":"pull / test-lora-linux / linux-job","jobName":"test-lora-linux / linux-job","conclusion":"failure","completed_at":"2026-05-05T17:38:29.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888246","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888246","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["RuntimeError: Command docker exec -t 0fcebe264521f6a7a3f3f53fe6d9138e2e6066e55fc6159a2efae37c3bc8a946 /exec failed with exit code 1"],"failure_lines":["RuntimeError: Command docker exec -t 0fcebe264521f6a7a3f3f53fe6d9138e2e6066e55fc6159a2efae37c3bc8a946 /exec failed with exit code 1"],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"}],"FLAKY":[],"BROKEN_TRUNK":[{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888471,"runnerName":"i-0ef904eab2a0d0582","authorEmail":"[email protected]","name":"pull / unittest / linux / linux-job","jobName":"unittest / linux / linux-job","conclusion":"failure","completed_at":"2026-05-05T17:40:12.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888471","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888471","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer"],"failure_lines":["FAILED examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer - AssertionError: tensor(False) is not true"],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"},{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888507,"runnerName":"i-0b3e545a4fe0fe4d9","authorEmail":"[email protected]","name":"pull / unittest / macos / macos-job","jobName":"unittest / macos / macos-job","conclusion":"cancelled","completed_at":"2026-05-05T18:12:20.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888507","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888507","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["##[error]The operation was canceled."],"failure_lines":["##[error]The operation was canceled."],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"},{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888345,"runnerName":"i-0397bba31d150a33c","authorEmail":"[email protected]","name":"pull / unittest-editable / linux / linux-job","jobName":"unittest-editable / linux / linux-job","conclusion":"failure","completed_at":"2026-05-05T17:43:13.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888345","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888345","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer"],"failure_lines":["FAILED examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer - AssertionError: tensor(False) is not true"],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"},{"workflowId":25389512697,"workflowUniqueId":63454257,"id":74459888356,"runnerName":"i-060bed30810816f1c","authorEmail":"[email protected]","name":"pull / unittest-editable / macos / macos-job","jobName":"unittest-editable / macos / macos-job","conclusion":"cancelled","completed_at":"2026-05-05T18:12:24.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512697/job/74459888356","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459888356","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["##[error]The operation was canceled."],"failure_lines":["##[error]The operation was canceled."],"failure_context":[],"time":"2026-05-05T16:41:49.000000000Z"},{"workflowId":25389512338,"workflowUniqueId":195669493,"id":74459881249,"runnerName":"i-069c607861b8c1742","authorEmail":"[email protected]","name":"Test CUDA Builds / unittest-cuda / linux-job","jobName":"unittest-cuda / linux-job","conclusion":"failure","completed_at":"2026-05-05T17:30:15.000000000Z","html_url":"https://github.com/pytorch/executorch/actions/runs/25389512338/job/74459881249","logUrl":"https://ossci-raw-job-status.s3.amazonaws.com/log/pytorch/executorch/74459881249","head_branch":"gemma4-31b-quant-framework","pr_number":19213,"head_sha":"5b54f50309f67edfc57411a91fc683e1b44891ab","head_sha_timestamp":"2026-05-05T15:01:35.000000000Z","failure_captures":["backends/cuda/tests/test_int4_matmul.py::TestDequantThenMatmul::test_prefill_short"],"failure_lines":["FAILED backends/cuda/tests/test_int4_matmul.py::TestDequantThenMatmul::test_prefill_short - AssertionError: False is not true : fused vs dequant M=64 [2048x2048]: max_abs_err=1.0000"],"failure_context":[],"time":"2026-05-05T16:41:46.000000000Z"}],"UNSTABLE":[],"AWAITING_APPROVAL":[]}