run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bpf-v0-c4-v3-mkmlizer
Waiting for job on cycy233-l3-bpf-v0-c4-v3-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ /___/ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ belonging to: ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bpf-v0-c4-v3-mkmlizer: Downloaded to shared memory in 32.580s
cycy233-l3-bpf-v0-c4-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprup0qef6, device:0
cycy233-l3-bpf-v0-c4-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bpf-v0-c4-v3-mkmlizer: quantized model in 26.138s
cycy233-l3-bpf-v0-c4-v3-mkmlizer: Processed model cycy233/L3-bpf-v0-c4 in 58.718s
cycy233-l3-bpf-v0-c4-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bpf-v0-c4-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bpf-v0-c4-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3
cycy233-l3-bpf-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3/config.json
cycy233-l3-bpf-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3/special_tokens_map.json
cycy233-l3-bpf-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3/tokenizer_config.json
cycy233-l3-bpf-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3/tokenizer.json
cycy233-l3-bpf-v0-c4-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v3/flywheel_model.0.safetensors
cycy233-l3-bpf-v0-c4-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:07, 36.70it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 58.84it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:03, 68.36it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:03, 70.53it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:03, 76.89it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 88.99it/s]
Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 84.23it/s]
Loading 0: 26%|██▌ | 76/291 [00:00<00:02, 84.59it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:09, 21.91it/s]
Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 29.68it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 40.43it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 46.57it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 52.16it/s]
Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 57.86it/s]
Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 65.23it/s]
Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 70.25it/s]
Loading 0: 58%|█████▊ | 170/291 [00:03<00:01, 77.08it/s]
Loading 0: 62%|██████▏ | 179/291 [00:03<00:01, 74.59it/s]
Loading 0: 65%|██████▍ | 188/291 [00:04<00:04, 21.83it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 26.98it/s]
Loading 0: 70%|███████ | 205/291 [00:04<00:02, 33.09it/s]
Loading 0: 74%|███████▎ | 214/291 [00:04<00:01, 40.57it/s]
Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 55.09it/s]
Loading 0: 83%|████████▎ | 241/291 [00:04<00:00, 62.27it/s]
Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 72.18it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 74.01it/s]
Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 73.45it/s]
Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 75.79it/s]
Job cycy233-l3-bpf-v0-c4-v3-mkmlizer completed after 84.27s with status: succeeded
Stopping job with name cycy233-l3-bpf-v0-c4-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.35s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-bpf-v0-c4-v3
Waiting for inference service cycy233-l3-bpf-v0-c4-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-bpf-v0-c4-v3 ready after 140.68702387809753s
Pipeline stage MKMLDeployer completed in 141.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2888803482055664s
Received healthy response to inference request in 1.8968186378479004s
Received healthy response to inference request in 1.6398704051971436s
Received healthy response to inference request in 1.5808629989624023s
Received healthy response to inference request in 1.9496076107025146s
5 requests
0 failed requests
5th percentile: 1.5926644802093506
10th percentile: 1.6044659614562988
20th percentile: 1.6280689239501953
30th percentile: 1.6912600517272949
40th percentile: 1.7940393447875977
50th percentile: 1.8968186378479004
60th percentile: 1.9179342269897461
70th percentile: 1.9390498161315919
80th percentile: 2.017462158203125
90th percentile: 2.153171253204346
95th percentile: 2.221025800704956
99th percentile: 2.2753094387054444
mean time: 1.8712080001831055
Pipeline stage StressChecker completed in 10.85s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.65s
cycy233-l3-bpf-v0-c4_v3 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-bpf-v0-c4-v3-profiler
Waiting for inference service cycy233-l3-bpf-v0-c4-v3-profiler to be ready
Inference service cycy233-l3-bpf-v0-c4-v3-profiler ready after 150.33818292617798s
Pipeline stage MKMLProfilerDeployer completed in 150.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bpf-v0-c4-v3-profiler-predictor-00001-deploymencxhg6:/code/chaiverse_profiler_1725330776 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bpf-v0-c4-v3-profiler-predictor-00001-deploymencxhg6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725330776 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725330776/summary.json'
cycy233-l3-bpf-v0-c4_v3 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bpf-v0-c4_v3 status is now torndown due to DeploymentManager action