Add a batched-sequence KV cache layout and reorganize the control fac… #2681
kiymetakdemircuda-perf.yml
on: push
Get changed files
/
get-changed-files
4s
CI run decision
/
decide
34s
Matrix: export-models
Matrix: benchmark-cuda
Waiting for pending jobs
upload-benchmark-results
Annotations
3 errors and 37 warnings
|
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
Process completed with exit code 1.
|
|
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.
|
|
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, 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 (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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/
|
|
export-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / linux-job
No files were found with the provided path: /__w/_temp/artifacts/. No artifacts will be uploaded.
|
|
export-models (SocialLocalMobile/Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed, SocialLoca... / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v3... / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, non-quantized, openai_whisper-medium, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, non-quantized, openai_whisper-small, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, quantized-int4-weight-only, openai_whisper-large-v3... / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, quantized-int4-weight-only, nvidia_parakeet-tdt, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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, non-quantized, mistralai_Voxtral-Mini-3B-2507, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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 (nvidia/parakeet-tdt, non-quantized, nvidia_parakeet-tdt, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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 (mistralai/Voxtral-Mini-3B-2507, quantized-int4-tile-packed, mistralai_Voxtral-Mini... / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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 (mistralai/Voxtral-Mini-3B-2507, quantized-int4-weight-only, mistralai_Voxtral-Mini... / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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 (google/gemma-3-4b-it, non-quantized, google_gemma-3-4b-it, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
|
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 (nvidia/parakeet-tdt, quantized-int4-tile-packed, nvidia_parakeet-tdt, 50) / linux-job
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
model-google_gemma-3-4b-it-non-quantized
|
6.25 GB |
sha256:9af869c2705314c4e9c6477052d9e96746e5ecd767bfa72b4d7f0308cb86360e
|
|
|
model-mistralai_Voxtral-Mini-3B-2507-non-quantized
|
6.82 GB |
sha256:0036438d0fc6c0a5629e781b0cd669de4f62cd39b57bbfcd38740b71fed0189d
|
|
|
model-mistralai_Voxtral-Mini-3B-2507-quantized-int4-tile-packed
|
2.88 GB |
sha256:40fa5a6a79194322ff9f8fe46159143f015991b25f8f0171886dcb1289c53a74
|
|
|
model-mistralai_Voxtral-Mini-3B-2507-quantized-int4-weight-only
|
6.2 GB |
sha256:560f19206a9ccfa30f2b18d239530743cac1eb7a81dfce083ba974bd6aae449c
|
|
|
model-nvidia_parakeet-tdt-non-quantized
|
953 MB |
sha256:c4e2c8e90124c4dfbc12682efe5c3ce0702a414078d6e0192cdfa8795fe1b674
|
|
|
model-nvidia_parakeet-tdt-quantized-int4-tile-packed
|
445 MB |
sha256:8e7739dea45a691158531aa69b248c9cc8ec019005184e60d3a16baa21752c75
|
|
|
model-nvidia_parakeet-tdt-quantized-int4-weight-only
|
434 MB |
sha256:c00f887b88cb002ba0b324b72ce7154ac2297758632d9f397866bb393b4d184f
|
|
|
model-openai_whisper-large-v3-turbo-non-quantized
|
1.18 GB |
sha256:4db59c388b10e8d36b81e1fdd260b69a4ca26f3f7509993155378109b73a6954
|
|
|
model-openai_whisper-large-v3-turbo-quantized-int4-tile-packed
|
492 MB |
sha256:0568ea37d1cb8e3b7a27eb641fb4464b2a8e89d5f075e1d9e43a842b622be656
|
|
|
model-openai_whisper-large-v3-turbo-quantized-int4-weight-only
|
571 MB |
sha256:a9cd011e16ed3635056a1cfc562913f4a0fbfcf82101c1a55d0134ce4d435681
|
|
|
model-openai_whisper-medium-non-quantized
|
1.12 GB |
sha256:b386d00097e2c60fed3968bf124e433f7d5b7f8e0557b834634ce28eea67d6f6
|
|
|
model-openai_whisper-medium-quantized-int4-tile-packed
|
472 MB |
sha256:0be045d7d19406fa21a01ec40ebc91b741eb2c32635d1edb5ae6796c2d45437e
|
|
|
model-openai_whisper-medium-quantized-int4-weight-only
|
847 MB |
sha256:70c7489811a34750adea450be15652b36ce5159cc6c4fc284b9fb59a208d3e7c
|
|
|
model-openai_whisper-small-non-quantized
|
363 MB |
sha256:7f8c08a3ac810dcebca7078623696a681439c828a35b2b65680d265f16fdd4cd
|
|
|
model-openai_whisper-small-quantized-int4-tile-packed
|
173 MB |
sha256:d2b8a44ee54c88ce2e2f3f9d7826e8a09f8a3d2b34a9a64fb8f9275c405a3c37
|
|
|
model-openai_whisper-small-quantized-int4-weight-only
|
279 MB |
sha256:cc4462022019886a584d998398c104bc68463a65321c4e44c1aab50f66e11ab3
|
|