Skip to content

Enable 128k context for Gemma4-31B CUDA #14070

Enable 128k context for Gemma4-31B CUDA

Enable 128k context for Gemma4-31B CUDA #14070

Triggered via pull request June 17, 2026 01:50
Status Success
Total duration 1h 21m 5s
Artifacts 17

cuda.yml

on: pull_request
Get changed files  /  get-changed-files
4s
Get changed files / get-changed-files
CI run decision  /  decide
30s
CI run decision / decide
Matrix: export-model-cuda-artifact
Matrix: test-cuda-builds
test-models-cuda  /  linux-job
46m 44s
test-models-cuda / linux-job
unittest-cuda  /  linux-job
54m 16s
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

128 errors and 40 warnings
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
Process completed with exit code 1.
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
Process completed with exit code 1.
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
Process completed with exit code 1.
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
Process completed with exit code 1.
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-model-cuda-artifact (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-model-cuda-artifact (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
export-model-cuda-artifact (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
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, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
Process completed with exit code 1.
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
[OSDC] Step script exited with code 1. This is a script/workflow error, not an infrastructure issue. Check the step logs above for the actual failure.
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
CI run decision / decide
Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: actions/checkout@v4. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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-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 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 16th, 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 (unsloth, gemma-4-31B-it-GGUF, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 16th, 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, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 (unsloth, gemma-4-31B-it-GGUF, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 16th, 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 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. Actions will be forced to run with Node.js 24 by default starting June 16th, 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/

Artifacts

Produced during runtime
Name Size Digest
Qwen-Qwen3-0.6B-cuda-non-quantized
1.1 GB
sha256:c0986070abbe72af75eea15486420ab7acf8e8b9c0b75dbd2b7fb2e71955b89d
Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed
559 MB
sha256:a9c20469423deb5cf93e2746096030524683c3ac6449058241bed909d8a88661
SocialLocalMobile-Qwen3.5-35B-A3B-HQQ-INT4-cuda-quantized-int4-tile-packed
14.6 GB
sha256:86cfeebf3988b65d7528e31223b62aa4c330d9f8baed43536c39e798ee3cec12
facebook-dinov2-small-imagenet1k-1-layer-cuda-non-quantized
34.6 MB
sha256:dcb1f710a2d890bd57d1240bcb962c078eed098212ab1f54cd0f4d021cc44f36
google-gemma-3-4b-it-cuda-non-quantized
7.22 GB
sha256:538805d90590865358ba688bd0e20618fd1b18da83c2692602ecd6efcc8fbe75
google-gemma-3-4b-it-cuda-quantized-int4-tile-packed
3.4 GB
sha256:22f7c43bf812d81210b8005b6fb86c5ab04397f1eec51c2f90301f35008c98f1
mistralai-Voxtral-Mini-3B-2507-cuda-non-quantized
6.82 GB
sha256:f749396ec9e6aa93b2a57085b0fa82c996e03d362824c24b7a78d16a700e0f60
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-tile-packed
2.88 GB
sha256:07cfa767a2de65dce40772169c2102fcb9484cc82cb45b462eefb1617d36f9c6
mistralai-Voxtral-Mini-3B-2507-cuda-quantized-int4-weight-only
6.2 GB
sha256:ec51607ceef4f4546e5028cd491339b1a16966913279a68162a41bef844c111e
mistralai-Voxtral-Mini-4B-Realtime-2602-cuda-quantized-int4-tile-packed
2.71 GB
sha256:12a1ae579133e0bf179d40220d495968daa138fec1b7bd7a0977faa743b2838d
nvidia-diar_streaming_sortformer_4spk-v2-cuda-non-quantized
436 MB
sha256:d4ae3441f8bb5c766574d1ec2db9577cdc90708723f8aeb5a3f9e2231588b109
nvidia-parakeet-tdt-cuda-non-quantized
952 MB
sha256:d4c8e36fae0349611a1858d19f1cb47217875ad258f0ebe3913b308d8a0782c0
nvidia-parakeet-tdt-cuda-quantized-int4-tile-packed
443 MB
sha256:e372174c034c86d92e76eeb0edd199713c94c987261aefb9dab07c7de8cf0816
openai-whisper-large-v3-turbo-cuda-quantized-int4-tile-packed
491 MB
sha256:8ea71a1127581f371ddf22c754b30039faf3a968fd99293aeff187c9571be259
openai-whisper-large-v3-turbo-cuda-quantized-int4-weight-only
570 MB
sha256:1435dd33bfab8db6ffd81c60157740df8fa0a23399c02dde94b71aba80d83886
openai-whisper-small-cuda-non-quantized
362 MB
sha256:b3cfc5d3494aeae91eee74fe334808a892d291cfc2182f0f9a14c8bea9e5777c
unsloth-gemma-4-31B-it-GGUF-cuda-quantized-int4-tile-packed
18.8 GB
sha256:aa4d2ad0ab376df99a91e82b38747286d3c26733182f5040ed6fc29ef92c1ecc