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 chaiml-nis-qwen32b-sim-98336-v16-mkmlizer
Waiting for job on chaiml-nis-qwen32b-sim-98336-v16-mkmlizer to finish
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Version: 0.27.1+vampire_v3 ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ belonging to: ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ║ ║
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: Downloaded to shared memory in 85.243s
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl78m4f5v, device:0
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: quantized model in 59.089s
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: Processed model ChaiML/nis-qwen32b-simpoexp1-s1-pref-1295datav1sft-try2 in 144.333s
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/config.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/special_tokens_map.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/added_tokens.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/tokenizer_config.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/merges.txt
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/vocab.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/tokenizer.json
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/flywheel_model.2.safetensors
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-qwen32b-sim-98336-v16/flywheel_model.0.safetensors
chaiml-nis-qwen32b-sim-98336-v16-mkmlizer:
Loading 0: 0%| | 0/771 [00:00<?, ?it/s]
Loading 0: 1%| | 4/771 [00:00<00:32, 23.49it/s]
Loading 0: 1%|▏ | 10/771 [00:00<00:18, 40.13it/s]
Loading 0: 2%|▏ | 16/771 [00:00<00:20, 36.93it/s]
Loading 0: 3%|▎ | 21/771 [00:00<00:18, 40.86it/s]
Loading 0: 4%|▎ | 28/771 [00:00<00:18, 39.63it/s]
Loading 0: 4%|▍ | 33/771 [00:00<00:17, 41.58it/s]
Loading 0: 5%|▍ | 38/771 [00:00<00:16, 43.23it/s]
Loading 0: 6%|▌ | 46/771 [00:01<00:17, 42.08it/s]
Loading 0: 7%|▋ | 51/771 [00:01<00:17, 41.40it/s]
Loading 0: 8%|▊ | 58/771 [00:01<00:14, 48.26it/s]
Loading 0: 8%|▊ | 65/771 [00:01<00:14, 49.07it/s]
Loading 0: 10%|▉ | 76/771 [00:01<00:10, 63.26it/s]
Loading 0: 11%|█▏ | 87/771 [00:01<00:09, 74.35it/s]
Loading 0: 12%|█▏ | 95/771 [00:01<00:08, 75.35it/s]
Loading 0: 14%|█▎ | 106/771 [00:02<00:11, 59.70it/s]
Loading 0: 15%|█▍ | 113/771 [00:02<00:11, 56.96it/s]
Loading 0: 16%|█▌ | 121/771 [00:02<00:11, 57.11it/s]
Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 68.02it/s]
Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 74.74it/s]
Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 79.71it/s]
Loading 0: 21%|██ | 161/771 [00:02<00:08, 75.16it/s]
Loading 0: 22%|██▏ | 169/771 [00:03<00:11, 50.85it/s]
Loading 0: 23%|██▎ | 176/771 [00:03<00:11, 51.25it/s]
Loading 0: 24%|██▍ | 184/771 [00:03<00:10, 56.91it/s]
Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 67.55it/s]
Loading 0: 26%|██▋ | 203/771 [00:03<00:08, 70.06it/s]
Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 67.11it/s]
Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 60.34it/s]
Loading 0: 30%|███ | 233/771 [00:04<00:10, 51.05it/s]
Loading 0: 32%|███▏ | 244/771 [00:04<00:08, 61.90it/s]
Loading 0: 33%|███▎ | 255/771 [00:04<00:07, 71.56it/s]
Loading 0: 34%|███▍ | 264/771 [00:04<00:06, 75.26it/s]
Loading 0: 35%|███▌ | 273/771 [00:04<00:06, 72.37it/s]
Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 62.99it/s]
Loading 0: 38%|███▊ | 294/771 [00:05<00:08, 54.48it/s]
Loading 0: 39%|███▉ | 302/771 [00:20<00:08, 54.48it/s]
Loading 0: 39%|███▉ | 303/771 [00:20<03:49, 2.04it/s]
Loading 0: 41%|████ | 313/771 [00:20<02:36, 2.93it/s]
Loading 0: 42%|████▏ | 321/771 [00:20<01:55, 3.89it/s]
Loading 0: 43%|████▎ | 329/771 [00:20<01:24, 5.22it/s]
Loading 0: 45%|████▍ | 346/771 [00:20<00:47, 8.88it/s]
Loading 0: 46%|████▌ | 353/771 [00:21<00:41, 10.10it/s]
Loading 0: 47%|████▋ | 364/771 [00:21<00:28, 14.22it/s]
Loading 0: 49%|████▊ | 375/771 [00:21<00:20, 19.53it/s]
Loading 0: 50%|████▉ | 383/771 [00:21<00:16, 23.92it/s]
Loading 0: 51%|█████ | 391/771 [00:21<00:13, 28.48it/s]
Loading 0: 53%|█████▎ | 406/771 [00:22<00:10, 35.66it/s]
Loading 0: 54%|█████▎ | 413/771 [00:22<00:10, 34.92it/s]
Loading 0: 55%|█████▍ | 424/771 [00:22<00:07, 44.58it/s]
Loading 0: 56%|█████▋ | 435/771 [00:22<00:06, 54.66it/s]
Loading 0: 58%|█████▊ | 444/771 [00:22<00:05, 60.78it/s]
Loading 0: 59%|█████▉ | 453/771 [00:22<00:05, 61.97it/s]
Loading 0: 60%|██████ | 466/771 [00:22<00:05, 55.94it/s]
Loading 0: 61%|██████▏ | 473/771 [00:23<00:06, 47.92it/s]
Loading 0: 63%|██████▎ | 484/771 [00:23<00:04, 58.47it/s]
Loading 0: 64%|██████▍ | 495/771 [00:23<00:04, 68.19it/s]
Loading 0: 65%|██████▌ | 504/771 [00:23<00:03, 72.01it/s]
Loading 0: 67%|██████▋ | 513/771 [00:23<00:03, 69.08it/s]
Loading 0: 68%|██████▊ | 526/771 [00:23<00:04, 58.32it/s]
Loading 0: 69%|██████▉ | 533/771 [00:24<00:04, 49.70it/s]
Loading 0: 71%|███████ | 544/771 [00:24<00:03, 60.08it/s]
Loading 0: 72%|███████▏ | 555/771 [00:24<00:03, 69.64it/s]
Loading 0: 73%|███████▎ | 564/771 [00:24<00:02, 73.38it/s]
Loading 0: 74%|███████▍ | 573/771 [00:24<00:02, 70.16it/s]
Loading 0: 76%|███████▌ | 586/771 [00:24<00:03, 58.73it/s]
Loading 0: 77%|███████▋ | 593/771 [00:25<00:03, 50.10it/s]
Loading 0: 78%|███████▊ | 604/771 [00:25<00:02, 60.41it/s]
Loading 0: 80%|███████▉ | 615/771 [00:25<00:02, 70.02it/s]
Loading 0: 81%|████████ | 624/771 [00:25<00:02, 73.21it/s]
Loading 0: 81%|████████ | 626/771 [00:40<00:01, 73.21it/s]
Loading 0: 81%|████████▏ | 627/771 [00:40<01:25, 1.69it/s]
Loading 0: 82%|████████▏ | 635/771 [00:40<00:56, 2.41it/s]
Loading 0: 84%|████████▍ | 646/771 [00:40<00:33, 3.72it/s]
Loading 0: 85%|████████▍ | 653/771 [00:41<00:25, 4.70it/s]
Loading 0: 86%|████████▌ | 664/771 [00:41<00:14, 7.20it/s]
Loading 0: 88%|████████▊ | 675/771 [00:41<00:09, 10.55it/s]
Loading 0: 89%|████████▊ | 683/771 [00:41<00:06, 13.61it/s]
Loading 0: 90%|████████▉ | 691/771 [00:41<00:04, 17.23it/s]
Loading 0: 92%|█████████▏| 706/771 [00:41<00:02, 23.89it/s]
Loading 0: 92%|█████████▏| 713/771 [00:42<00:02, 25.33it/s]
Loading 0: 94%|█████████▍| 724/771 [00:42<00:01, 33.65it/s]
Loading 0: 95%|█████████▌| 735/771 [00:42<00:00, 42.82it/s]
Loading 0: 96%|█████████▋| 743/771 [00:42<00:00, 48.00it/s]
Loading 0: 97%|█████████▋| 751/771 [00:42<00:00, 50.46it/s]
Loading 0: 99%|█████████▉| 766/771 [00:43<00:00, 38.18it/s]
Job chaiml-nis-qwen32b-sim-98336-v16-mkmlizer completed after 187.78s with status: succeeded
Stopping job with name chaiml-nis-qwen32b-sim-98336-v16-mkmlizer
Pipeline stage MKMLizer completed in 188.81s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-qwen32b-sim-98336-v16
Waiting for inference service chaiml-nis-qwen32b-sim-98336-v16 to be ready
Inference service chaiml-nis-qwen32b-sim-98336-v16 ready after 100.81925439834595s
Pipeline stage MKMLDeployer completed in 101.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.196216344833374s
Received healthy response to inference request in 2.8144278526306152s
Received healthy response to inference request in 3.0437231063842773s
Received healthy response to inference request in 2.5585851669311523s
Received healthy response to inference request in 3.06352162361145s
5 requests
0 failed requests
5th percentile: 2.609753704071045
10th percentile: 2.6609222412109377
20th percentile: 2.7632593154907226
30th percentile: 2.860286903381348
40th percentile: 2.9520050048828126
50th percentile: 3.0437231063842773
60th percentile: 3.0516425132751466
70th percentile: 3.059561920166016
80th percentile: 3.090060567855835
90th percentile: 3.1431384563446043
95th percentile: 3.169677400588989
99th percentile: 3.190908555984497
mean time: 2.935294818878174
Pipeline stage StressChecker completed in 17.29s
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 0.95s
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 0.96s
Shutdown handler de-registered
chaiml-nis-qwen32b-sim_98336_v16 status is now deployed due to DeploymentManager action
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 3096.89s
Shutdown handler de-registered
chaiml-nis-qwen32b-sim_98336_v16 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-qwen32b-sim_98336_v16 status is now torndown due to DeploymentManager action