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-llama-8b-nis-800-59411-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800-59411-v1-mkmlizer to finish
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ║ ║
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: Downloaded to shared memory in 28.788s
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc already exists in ChaiML
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpcf2a_q9r, device:0
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: quantized model in 19.773s
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retune_lin_bestep_573acc in 48.562s
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia/config.json
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-800-59411-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800-59411-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800-59411-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:09, 31.55it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 51.04it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:06, 44.98it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:05, 45.25it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:05, 48.67it/s]
Loading 0: 12%|█▏ | 35/291 [00:00<00:05, 46.71it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 47.33it/s]
Loading 0: 16%|█▌ | 46/291 [00:01<00:05, 44.28it/s]
Loading 0: 18%|█▊ | 51/291 [00:01<00:05, 44.30it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 49.39it/s]
Loading 0: 22%|██▏ | 64/291 [00:01<00:05, 45.14it/s]
Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 44.71it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.77it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 47.02it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 28.73it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 34.11it/s]
Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 35.74it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 38.32it/s]
Loading 0: 37%|███▋ | 109/291 [00:02<00:04, 38.86it/s]
Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 39.11it/s]
Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 45.61it/s]
Loading 0: 43%|████▎ | 126/291 [00:02<00:03, 46.33it/s]
Loading 0: 45%|████▌ | 131/291 [00:03<00:04, 39.58it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 48.51it/s]
Loading 0: 50%|████▉ | 145/291 [00:03<00:03, 46.72it/s]
Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 44.62it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 49.89it/s]
Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 46.15it/s]
Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 45.62it/s]
Loading 0: 60%|██████ | 176/291 [00:03<00:02, 54.15it/s]
Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 46.77it/s]
Loading 0: 65%|██████▍ | 188/291 [00:04<00:03, 33.49it/s]
Loading 0: 66%|██████▋ | 193/291 [00:04<00:02, 34.49it/s]
Loading 0: 68%|██████▊ | 198/291 [00:04<00:02, 36.46it/s]
Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 32.66it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:01, 41.06it/s]
Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 42.93it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 35.64it/s]
Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 42.20it/s]
Loading 0: 80%|████████ | 233/291 [00:05<00:01, 41.18it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 40.83it/s]
Loading 0: 84%|████████▎ | 243/291 [00:05<00:01, 41.31it/s]
Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 34.49it/s]
Loading 0: 88%|████████▊ | 255/291 [00:06<00:00, 41.54it/s]
Loading 0: 89%|████████▉ | 260/291 [00:06<00:00, 41.38it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 43.27it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 41.76it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 40.77it/s]
Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 42.31it/s]
Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 36.31it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 29.40it/s]
Job chaiml-llama-8b-nis-800-59411-v1-mkmlizer completed after 74.35s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800-59411-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.89s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-800-59411-v1
Waiting for inference service chaiml-llama-8b-nis-800-59411-v1 to be ready
Inference service chaiml-llama-8b-nis-800-59411-v1 ready after 211.32067155838013s
Pipeline stage MKMLDeployer completed in 212.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.121041297912598s
Received healthy response to inference request in 3.5851006507873535s
Received healthy response to inference request in 4.938067674636841s
Received healthy response to inference request in 3.5327093601226807s
Received healthy response to inference request in 5.003008842468262s
5 requests
0 failed requests
5th percentile: 3.5431876182556152
10th percentile: 3.55366587638855
20th percentile: 3.574622392654419
30th percentile: 3.6922887802124023
40th percentile: 3.9066650390625
50th percentile: 4.121041297912598
60th percentile: 4.447851848602295
70th percentile: 4.774662399291992
80th percentile: 4.951055908203125
90th percentile: 4.9770323753356935
95th percentile: 4.990020608901977
99th percentile: 5.000411195755005
mean time: 4.235985565185547
Pipeline stage StressChecker completed in 22.81s
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 0.67s
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 0.72s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_59411_v1 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 9083.68s
Shutdown handler de-registered
chaiml-llama-8b-nis-800_59411_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800_59411_v1 status is now torndown due to DeploymentManager action