Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name qwen-qwen2-5-14b-v3-mkmlizer
Waiting for job on qwen-qwen2-5-14b-v3-mkmlizer to finish
qwen-qwen2-5-14b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
qwen-qwen2-5-14b-v3-mkmlizer: ║ _____ __ __ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ /___/ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ Version: 0.12.8 ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ https://mk1.ai ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ belonging to: ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ Chai Research Corp. ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
qwen-qwen2-5-14b-v3-mkmlizer: ║ ║
qwen-qwen2-5-14b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
qwen-qwen2-5-14b-v3-mkmlizer: Downloaded to shared memory in 42.271s
qwen-qwen2-5-14b-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphn7tke2q, device:0
qwen-qwen2-5-14b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-tyler-james_92283_v1: HTTPConnectionPool(host='jellywibble-tyler-james-92283-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
qwen-qwen2-5-14b-v3-mkmlizer: quantized model in 36.751s
qwen-qwen2-5-14b-v3-mkmlizer: Processed model Qwen/Qwen2.5-14B in 79.023s
qwen-qwen2-5-14b-v3-mkmlizer: creating bucket guanaco-mkml-models
qwen-qwen2-5-14b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
qwen-qwen2-5-14b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/config.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/added_tokens.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/tokenizer_config.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/special_tokens_map.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/merges.txt
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/vocab.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/tokenizer.json
qwen-qwen2-5-14b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/qwen-qwen2-5-14b-v3/flywheel_model.0.safetensors
qwen-qwen2-5-14b-v3-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 15/579 [00:00<00:03, 142.02it/s]
Loading 0: 5%|▌ | 30/579 [00:00<00:04, 129.67it/s]
Loading 0: 9%|▉ | 51/579 [00:00<00:03, 162.42it/s]
Loading 0: 12%|█▏ | 68/579 [00:00<00:05, 98.44it/s]
Loading 0: 14%|█▍ | 81/579 [00:00<00:04, 105.53it/s]
Loading 0: 17%|█▋ | 96/579 [00:00<00:04, 111.31it/s]
Loading 0: 19%|█▉ | 109/579 [00:00<00:04, 115.99it/s]
Loading 0: 22%|██▏ | 127/579 [00:01<00:03, 132.35it/s]
Loading 0: 25%|██▍ | 142/579 [00:01<00:04, 99.70it/s]
Loading 0: 27%|██▋ | 154/579 [00:01<00:04, 101.10it/s]
Loading 0: 30%|██▉ | 171/579 [00:01<00:03, 115.00it/s]
Loading 0: 32%|███▏ | 185/579 [00:01<00:03, 117.40it/s]
Loading 0: 36%|███▌ | 207/579 [00:01<00:02, 137.63it/s]
Loading 0: 38%|███▊ | 222/579 [00:01<00:02, 136.76it/s]
Loading 0: 41%|████ | 237/579 [00:02<00:03, 99.32it/s]
Loading 0: 44%|████▍ | 255/579 [00:02<00:02, 114.13it/s]
Loading 0: 46%|████▋ | 269/579 [00:02<00:02, 114.95it/s]
Loading 0: 50%|████▉ | 288/579 [00:02<00:02, 132.80it/s]
Loading 0: 52%|█████▏ | 303/579 [00:02<00:02, 135.15it/s]
Loading 0: 55%|█████▍ | 318/579 [00:02<00:02, 95.33it/s]
Loading 0: 59%|█████▊ | 339/579 [00:02<00:02, 114.46it/s]
Loading 0: 61%|██████ | 353/579 [00:03<00:01, 115.96it/s]
Loading 0: 65%|██████▍ | 375/579 [00:03<00:01, 136.33it/s]
Loading 0: 68%|██████▊ | 391/579 [00:03<00:01, 137.14it/s]
Loading 0: 70%|███████ | 406/579 [00:03<00:01, 112.94it/s]
Loading 0: 72%|███████▏ | 419/579 [00:03<00:01, 110.27it/s]
Loading 0: 75%|███████▌ | 436/579 [00:03<00:01, 118.77it/s]
Loading 0: 78%|███████▊ | 449/579 [00:03<00:01, 121.48it/s]
Loading 0: 81%|████████ | 469/579 [00:03<00:00, 141.03it/s]
Loading 0: 84%|████████▎ | 484/579 [00:04<00:00, 140.48it/s]
Loading 0: 86%|████████▌ | 499/579 [00:04<00:00, 96.36it/s]
Loading 0: 89%|████████▉ | 518/579 [00:04<00:00, 115.77it/s]
Loading 0: 92%|█████████▏| 532/579 [00:19<00:13, 3.53it/s]
Loading 0: 94%|█████████▍| 546/579 [00:19<00:06, 4.82it/s]
Loading 0: 98%|█████████▊| 566/579 [00:19<00:01, 7.40it/s]
Job qwen-qwen2-5-14b-v3-mkmlizer completed after 104.77s with status: succeeded
Stopping job with name qwen-qwen2-5-14b-v3-mkmlizer
Pipeline stage MKMLizer completed in 105.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service qwen-qwen2-5-14b-v3
Waiting for inference service qwen-qwen2-5-14b-v3 to be ready
Inference service qwen-qwen2-5-14b-v3 ready after 110.68278288841248s
Pipeline stage MKMLDeployer completed in 111.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.654064416885376s
Received healthy response to inference request in 2.00323748588562s
Received healthy response to inference request in 1.4078361988067627s
Received healthy response to inference request in 1.9311201572418213s
Received healthy response to inference request in 2.052227020263672s
5 requests
0 failed requests
5th percentile: 1.5124929904937745
10th percentile: 1.617149782180786
20th percentile: 1.8264633655548095
30th percentile: 1.9455436229705811
40th percentile: 1.9743905544281006
50th percentile: 2.00323748588562
60th percentile: 2.022833299636841
70th percentile: 2.0424291133880614
80th percentile: 2.172594499588013
90th percentile: 2.4133294582366944
95th percentile: 2.533696937561035
99th percentile: 2.6299909210205077
mean time: 2.0096970558166505
Pipeline stage StressChecker completed in 11.31s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.66s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.63s
Shutdown handler de-registered
qwen-qwen2-5-14b_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service qwen-qwen2-5-14b-v3-profiler
Waiting for inference service qwen-qwen2-5-14b-v3-profiler to be ready
Inference service qwen-qwen2-5-14b-v3-profiler ready after 150.60608077049255s
Pipeline stage MKMLProfilerDeployer completed in 151.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/qwen-qwen2-5-14b-v3-profiler-predictor-00001-deployment-64rj4tl:/code/chaiverse_profiler_1744404505 --namespace tenant-chaiml-guanaco
kubectl exec -it qwen-qwen2-5-14b-v3-profiler-predictor-00001-deployment-64rj4tl --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1744404505 && python profiles.py profile --best_of_n 8 --auto_batch 5 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1744404505/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2660.41s
Shutdown handler de-registered
qwen-qwen2-5-14b_v3 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen2-5-14b_v3 status is now torndown due to DeploymentManager action