Skip to content

Add fused GatedDeltaNet decode Triton kernel #12543

Add fused GatedDeltaNet decode Triton kernel

Add fused GatedDeltaNet decode Triton kernel #12543

Triggered via pull request April 14, 2026 06:39
Status Failure
Total duration 2h 54m 58s
Artifacts 16

cuda.yml

on: pull_request
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
test-models-cuda  /  linux-job
43m 22s
test-models-cuda / linux-job
unittest-cuda  /  linux-job
35m 26s
unittest-cuda / linux-job
Matrix: test-cuda-pybind
Matrix: test-model-cuda-e2e
check-all-cuda-builds
2s
check-all-cuda-builds
Fit to window
Zoom out
Zoom in

Annotations

3 errors and 39 warnings
unittest-cuda / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
Process completed with exit code 1.
test-executorch-cuda-build-13.0 / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-executorch-cuda-build-12.6 / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-executorch-cuda-build-12.8 / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-executorch-cuda-build-12.9 / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
unittest-cuda / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-models-cuda / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-cuda-pybind (qwen3-0.6b, --quantize, Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-cuda-pybind (qwen3-0.6b, Qwen-Qwen3-0.6B-cuda-non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-cuda-pybind (gemma3-4b, --quantize, google-gemma-3-4b-it-cuda-quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, nick-fields/retry@3e91a01664abd3c5cd539100d10d33b9c5b68482, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: ./test-infra/.github/actions/setup-ssh, actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 2nd, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/

Artifacts

Produced during runtime
Name Size Digest
Qwen-Qwen3-0.6B-cuda-non-quantized
1.1 GB
sha256:d5b782df9e3ac8aba3d3bdc7c663126afae276c6c1a93255d29e9d8cd924924c
Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed
560 MB
sha256:cfa8c3f8739cb655044e8019921bee658c876d66663611fb2abf95d5c87d43e3
SocialLocalMobile-Qwen3.5-35B-A3B-HQQ-INT4-cuda-quantized-int4-tile-packed
14.7 GB
sha256:2fa7c4b506debe0a5cad95ae646c6adddaf080967c7cdfbbdc6eb9292e4e1054
facebook-dinov2-small-imagenet1k-1-layer-cuda-non-quantized
34.6 MB
sha256:5cc9a3f1f9fa5fdc04ffdf3e955c4facb414ccc59a00b6d160901ed732ed9482
google-gemma-3-4b-it-cuda-non-quantized
7.22 GB
sha256:35bb2ad988f17dde0d60350f81feb1a643b41beb89ff19bf3613e2794093cd6e
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed
3.4 GB
sha256:a341165b35f294d9edb9a9a22715ff937e4b2c744b320a0bf84509cdfd6f6014
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized
6.82 GB
sha256:0fcb84f14e08aa21ab8f1543718d442d1af931a50e755446f92699f976d02210
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed
2.88 GB
sha256:40780c14ac8f44e3595977fc26496fed580f185349c9a4e9a84cc3037860cba6
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only
6.2 GB
sha256:8141e14731d1cadfe6d8a9017d52c5206e8143f67726e4dbe7dc28ae691febe0
mistralai-Voxtral-Mini-4B-Realtime-2602-cuda-quantized-int4-tile-packed
2.71 GB
sha256:8bf298c95fccba5b126c2415b859e5ac36abf4289f3cc2d8a17f77d1a65cd5c0
nvidia-diar_streaming_sortformer_4spk-v2-cuda-non-quantized
436 MB
sha256:31ccdaed5bd4887e905916c85f3a60aae8bd75ab613d91a565ac7773ae2ba529
nvidia-parakeet-tdt-cuda-non-quantized
952 MB
sha256:8e4c2c2c6539dc0f7cedce840adca8201563aa8a1619924ada8931a39c06324d
nvidia-parakeet-tdt-cuda-quantized-int4-tile-packed
443 MB
sha256:dd024bd75f70615e86893e6af04909cea82a7f3cc5ae6c47c50526b07cb11159
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed
491 MB
sha256:63b5896edb419eb4b637a955ed6cc0af040c1b77b99077eaa9f4ae7e8e566586
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only
570 MB
sha256:edb37264bbc8a3b31143b0fa1b4dbd8007d95fec7890f9539b3edb6b57bb9bb0
openai-whisper-small-cuda-non-quantized
361 MB
sha256:b9401d727730d9300abcc34531051be931e161c0ac056beee62c6311d2d0c982