Skip to content
Test Metal Backend

[ET-VK][matmul] Re-implement fp32/fp16 matmul and linear with tiled compute and blocked weight packing #10118

Sign in to view logs

[ET-VK][matmul] Re-implement fp32/fp16 matmul and linear with tiled compute and blocked weight packing

[ET-VK][matmul] Re-implement fp32/fp16 matmul and linear with tiled compute and blocked weight packing #10118

Run time

Learn about OS pricing on GitHub Actions
Job Run time
test-metal-backend-modules / macos-job
8m 40s
test-executorch-metal-build / macos-job
5m 11s
export-model-metal-artifact (openai, whisper-small, non-quantized) / macos-job
7m 21s
export-model-metal-artifact (openai, whisper-large-v3-turbo, quantized-int4-metal) / macos-job
7m 55s
export-model-metal-artifact (nvidia, parakeet-tdt, quantized-int4-metal) / macos-job
9m 36s
export-model-metal-artifact (openai, whisper-small, quantized-int4-metal) / macos-job
7m 24s
export-model-metal-artifact (openai, whisper-large-v3-turbo, non-quantized) / macos-job
7m 58s
export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job
14m 24s
export-model-metal-artifact (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job
22m 0s
export-model-metal-artifact (nvidia, parakeet-tdt, non-quantized) / macos-job
9m 32s
export-model-metal-artifact (mistralai, Voxtral-Mini-3B-2507, quantized-int4-metal) / macos-job
10m 38s
test-model-metal-e2e (nvidia, parakeet-tdt, non-quantized) / macos-job
4m 56s
test-model-metal-e2e (openai, whisper-large-v3-turbo, quantized-int4-metal) / macos-job
5m 55s
test-model-metal-e2e (nvidia, parakeet-tdt, quantized-int4-metal) / macos-job
4m 47s
test-model-metal-e2e (openai, whisper-large-v3-turbo, non-quantized) / macos-job
5m 54s
test-model-metal-e2e (mistralai, Voxtral-Mini-3B-2507, non-quantized) / macos-job
7m 25s
test-model-metal-e2e (mistralai, Voxtral-Mini-4B-Realtime-2602, quantized-int4-metal) / macos-job
9m 44s
test-model-metal-e2e (openai, whisper-small, non-quantized) / macos-job
5m 53s
test-model-metal-e2e (openai, whisper-small, quantized-int4-metal) / macos-job
5m 29s
test-model-metal-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-metal) / macos-job
5m 55s
2h 46m 37s