Skip to content
Test CUDA Builds

[cuda backend] splitk turboquant sdpa for decode #14122

Sign in to view logs

[cuda backend] splitk turboquant sdpa for decode

[cuda backend] splitk turboquant sdpa for decode #14122

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Get changed files / get-changed-files
4s
CI run decision / decide
32s
unittest-cuda / linux-job
55m 10s
test-models-cuda / linux-job
47m 20s
test-executorch-cuda-build-12.6 / linux-job
18m 45s
test-executorch-cuda-build-13.0 / linux-job
17m 24s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
24m 44s
export-model-cuda-artifact (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
34m 35s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
25m 29s
export-model-cuda-artifact (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
31m 34s
export-model-cuda-artifact (openai, whisper-small, non-quantized) / linux-job
16m 51s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
20m 20s
export-model-cuda-artifact (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
22m 25s
export-model-cuda-artifact (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
16m 46s
export-model-cuda-artifact (google, gemma-3-4b-it, non-quantized) / linux-job
30m 57s
export-model-cuda-artifact (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
27m 43s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, quantized-int4-tile-packed) / linux-job
19m 28s
export-model-cuda-artifact (nvidia, parakeet-tdt, non-quantized) / linux-job
25m 51s
export-model-cuda-artifact (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
43m 55s
export-model-cuda-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
27m 55s
export-model-cuda-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
23m 18s
export-model-cuda-artifact (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
53m 36s
export-model-cuda-artifact (Qwen, Qwen3-0.6B, non-quantized) / linux-job
17m 46s
check-all-cuda-builds
3s
test-cuda-pybind (qwen3-0.6b, Qwen-Qwen3-0.6B-cuda-non-quantized) / linux-job
19m 36s
test-cuda-pybind (qwen3-0.6b, --quantize, Qwen-Qwen3-0.6B-cuda-quantized-int4-tile-packed) / linux-job
19m 35s
test-cuda-pybind (gemma3-4b, --quantize, google-gemma-3-4b-it-cuda-quantized-int4-tile-packed) / linux-job
21m 31s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / linux-job
14m 6s
test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job
13m 59s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-weight-only) / linux-job
11m 16s
test-model-cuda-e2e (facebook, dinov2-small-imagenet1k-1-layer, non-quantized) / linux-job
7m 28s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job
24m 51s
test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job
9m 57s
test-model-cuda-e2e (google, gemma-3-4b-it, quantized-int4-tile-packed) / linux-job
13m 44s
test-model-cuda-e2e (nvidia, diar_streaming_sortformer_4spk-v2, non-quantized) / linux-job
10m 51s
test-model-cuda-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-tile-packed) / linux-job
26m 35s
test-model-cuda-e2e (nvidia, parakeet-tdt, quantized-int4-tile-packed) / linux-job
7m 32s
test-model-cuda-e2e (google, gemma-3-4b-it, non-quantized) / linux-job
9m 34s
test-model-cuda-e2e (unsloth, gemma-4-31B-it-GGUF, quantized-int4-tile-packed) / linux-job
18m 40s
test-model-cuda-e2e (SocialLocalMobile, Qwen3.5-35B-A3B-HQQ-INT4, quantized-int4-tile-packed) / linux-job
17m 35s
test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job
23m 54s
test-model-cuda-e2e (nvidia, parakeet-tdt, non-quantized) / linux-job
11m 44s
14h 44m 59s