Skip to content

[MLX] Reduce physical footprint memory in RingBufferKVCache for chunk… #1380

[MLX] Reduce physical footprint memory in RingBufferKVCache for chunk…

[MLX] Reduce physical footprint memory in RingBufferKVCache for chunk… #1380

Triggered via push June 17, 2026 23:42
Status Success
Total duration 1h 28m 12s
Artifacts 38

cuda-perf.yml

on: push
Get changed files  /  get-changed-files
4s
Get changed files / get-changed-files
CI run decision  /  decide
29s
CI run decision / decide
set-parameters
9s
set-parameters
Matrix: export-models
Matrix: benchmark-cuda
upload-benchmark-results
33s
upload-benchmark-results
Fit to window
Zoom out
Zoom in

Annotations

152 errors and 41 warnings
export-models (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-small, non-quantized, openai_whisper-small, 50) / 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-models (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / 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-models (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v3... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v3... / 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-models (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v3... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / 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-models (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v3... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v3... / 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-models (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v3... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / 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-models (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / 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-models (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / 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-models (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / 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-models (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / 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-models (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / 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-models (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Mini... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Mini... / 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-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Mini... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / 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-models (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / 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-models (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Mini... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Mini... / 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-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Mini... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / 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-models (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / 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-models (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / 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-models (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
export-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
export-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / 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-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / 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.
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / 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.
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / 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.
benchmark-cuda (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Min... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Min... / 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.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Min... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Min... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Min... / 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.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Min... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / 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.
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / 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.
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v... / 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.
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v... / 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.
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / 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.
benchmark-cuda (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / 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.
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / 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.
benchmark-cuda (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-small, non-quantized, openai_whisper-small, 50) / 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.
benchmark-cuda (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / 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.
benchmark-cuda (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / 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.
benchmark-cuda (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / 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.
benchmark-cuda (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / 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.
benchmark-cuda (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / 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.
benchmark-cuda (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
benchmark-cuda (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoc... / linux-job
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
benchmark-cuda (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoc... / 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.
benchmark-cuda (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoc... / linux-job
Not authorized to perform sts:AssumeRoleWithWebIdentity
CI run decision / decide
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@v4. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
set-parameters
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@v3, actions/setup-python@v4. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v3... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v3... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Mini... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Mini... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
export-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (nvidia/parakeet-tdt, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Min... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Min... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (mistralai/Voxtral-Mini-3B-2507, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-tile-packed, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (google/gemma-3-4b-it, quantized-int4-weight-only, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
benchmark-cuda (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoc... / linux-job
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683, actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093, actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02, aws-actions/configure-aws-credentials@67fbcbb121271f7775d2e7715933280b06314838, pmeier/pytest-results-action@a2c1430e2bddadbad9f49a6f9b879f062c6b19b1. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/
upload-benchmark-results
Node.js 20 is deprecated. The following actions target Node.js 20 but are being forced to run on Node.js 24: actions/checkout@v3, actions/download-artifact@v4, actions/setup-python@v4, aws-actions/configure-aws-credentials@v4. 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
model-SocialLocalMobile_Qwen3.5-35B-A3B-HQQ-INT4-quantized-int4-tile-packed
14.6 GB
sha256:394d3d40174e3636e4b5e82e9c3ecaea385446d1a2fd87d188e72b41e228e53d
model-google_gemma-3-4b-it-non-quantized
7.22 GB
sha256:0db35f3a76dbdbc73d1113f6689f310a57d29fd30cc5232da6b7adc93ccdf3a8
model-google_gemma-3-4b-it-quantized-int4-tile-packed
3.4 GB
sha256:f96e0f369bf864342bb3234975d52b9eeb655ee899c7178685b07743c16cd54f
model-google_gemma-3-4b-it-quantized-int4-weight-only
6.96 GB
sha256:e71a7545e3f799d2fa50d37822bd948f11374231d31ca49d7e79b8fff057f165
model-mistralai_Voxtral-Mini-3B-2507-non-quantized
6.82 GB
sha256:2e99a4048af7c50fdb00fcdeec75f33e053868276bd29aba06c89c6ba2e5ee06
model-mistralai_Voxtral-Mini-3B-2507-quantized-int4-tile-packed
2.88 GB
sha256:2b95a2b2d487675777c47891e193fd99724eb08bcd1aef59d177422c80e6894c
model-mistralai_Voxtral-Mini-3B-2507-quantized-int4-weight-only
6.2 GB
sha256:334075fbe40b08f2185ecc732ee3a4fb54f291bb32cdca655b94f47a97962212
model-nvidia_parakeet-tdt-non-quantized
952 MB
sha256:46b997054dec33b09d2ce8179e33c7d79d6611008b6194b09046388f3976cfcf
model-nvidia_parakeet-tdt-quantized-int4-tile-packed
443 MB
sha256:3597b6e472f54c7a2f21b42913f18b13cb16fa59f935ca1635629854e936ebc6
model-nvidia_parakeet-tdt-quantized-int4-weight-only
433 MB
sha256:0f1cf0de0bde94cfd7605ebc01916f75281af560a2bb75ad1f9d5e70b37ec0a2
model-openai_whisper-large-v3-turbo-non-quantized
1.18 GB
sha256:014909c6f647e9767a0449338c87ea0bd6ea1c7e6008cb9f99ab4ad5335aed2d
model-openai_whisper-large-v3-turbo-quantized-int4-tile-packed
491 MB
sha256:c9268482efabdaa524d4cd2e705e9cfbba49a39569b4484f3d2521f906655d6d
model-openai_whisper-large-v3-turbo-quantized-int4-weight-only
570 MB
sha256:71b4f5d32ff87f334525fb9a585cd4ee63f6a43a8d1a18c73326ff745d0312e2
model-openai_whisper-medium-non-quantized
1.12 GB
sha256:4350c2cb9396be41f692c5d00ca7e16c24a5b70a8f467f8e5b36c3129981b178
model-openai_whisper-medium-quantized-int4-tile-packed
471 MB
sha256:e7e6d0d8e765543eb075006a8514b2a7385a2357570b903408a2612137886427
model-openai_whisper-medium-quantized-int4-weight-only
846 MB
sha256:a1f8a9c460346f4151638a31b5e7f3a0f3ffc9875edee940dbc1c0f92e048c25
model-openai_whisper-small-non-quantized
362 MB
sha256:e60edc1c29eb44817cc0f6f0e9bfd9c579e3b0d0fdd477a6046cae5fdd712b3d
model-openai_whisper-small-quantized-int4-tile-packed
172 MB
sha256:fbd545772ebc70c7cd7290d6b552c02892c46b4b262031ae62bb17a0797aa053
model-openai_whisper-small-quantized-int4-weight-only
278 MB
sha256:2ba3c16d89b9e8b98351074ae34d989c0d7f0c9f92a71d15eee2c736b46def78
results-SocialLocalMobile_Qwen3.5-35B-A3B-HQQ-INT4-quantized-int4-tile-packed
1.92 KB
sha256:b1a7c41bba1122dedfed3de3aa29242651dbbcaebf24e95c90683fcab3a2129a
results-google_gemma-3-4b-it-non-quantized
1.79 KB
sha256:e088869c5d80d1b410c14c9f2edb0d79adf8689c4cecbff361baf18cc5c3cb36
results-google_gemma-3-4b-it-quantized-int4-tile-packed
1.83 KB
sha256:7c10c5e27b9ddf7027104e8bc1dc17c10acff04cf49a7c8a020fc8829f5315ab
results-google_gemma-3-4b-it-quantized-int4-weight-only
1.81 KB
sha256:cb77d9f2a9fe8ee595a2b418afb1ea4661192299b23378bbc810e884ce17bca3
results-mistralai_Voxtral-Mini-3B-2507-non-quantized
1.79 KB
sha256:4d88e2df35b441451a967759ea897ef03c6a815b952951fe6a42b52ad2efe277
results-mistralai_Voxtral-Mini-3B-2507-quantized-int4-tile-packed
1.83 KB
sha256:fe795a673c3237cf821ca39d92fd9aa2e200023f38a739bd21b0c4d52e496545
results-mistralai_Voxtral-Mini-3B-2507-quantized-int4-weight-only
1.82 KB
sha256:9c500c47bf195b2142f4a5a65f6a199533a0238434d09d2402d949e1bf39ad7d
results-nvidia_parakeet-tdt-non-quantized
1.77 KB
sha256:d6be74f89e811f52b47efe717d6049d099d9295eea57cce665928d643952334d
results-nvidia_parakeet-tdt-quantized-int4-tile-packed
1.77 KB
sha256:9c7e6600ac5b10a86ea8b198a49198fae4069cddb519979b1599b918af9d3121
results-nvidia_parakeet-tdt-quantized-int4-weight-only
1.79 KB
sha256:96331e71249d30b2fe7452064aae0a8beb6a1d5f4787be22fbaa668f79d9122c
results-openai_whisper-large-v3-turbo-non-quantized
1.81 KB
sha256:cb513fe90968cbc1ca3e403cc5ad4af88d90e28684572735efbefef879103934
results-openai_whisper-large-v3-turbo-quantized-int4-tile-packed
1.85 KB
sha256:aa4ada8fdd89cae30bbf1a011a7647d0d0e045833a5ec725907de036fe8274c6
results-openai_whisper-large-v3-turbo-quantized-int4-weight-only
1.83 KB
sha256:a5513c93c572fa467ada651408a03850e00b284ef35270b8311d2416758f2e34
results-openai_whisper-medium-non-quantized
1.8 KB
sha256:51cdf0a6aa483986bda0b01f9edca75118819e7dbf3e00c852608b26c0f605ef
results-openai_whisper-medium-quantized-int4-tile-packed
1.83 KB
sha256:23457eeb5315851b340d71e05ddb8c8887f284c1aa4817fa0e3efb96e4f9f711
results-openai_whisper-medium-quantized-int4-weight-only
1.75 KB
sha256:8575c25d860be78f9a81c4865612f7a590c3a16e80d4d475312323aeb4d2bb24
results-openai_whisper-small-non-quantized
1.75 KB
sha256:74d19fc1070029acc01156ef867a5881fa80742bc508c65a1a1d4d7393d292d2
results-openai_whisper-small-quantized-int4-tile-packed
1.82 KB
sha256:36d626e60e15c509d45e291aa9cb83c566b105d525f61f6d87811ab0cc184362
results-openai_whisper-small-quantized-int4-weight-only
1.84 KB
sha256:948443e6ae3f9b3d4aca55c07eb19ec40c462cc0632a2eda3acc2e52ca0cac82