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-llama31-mer-v2-44570-v59-mkmlizer
Waiting for job on chaiml-llama31-mer-v2-44570-v59-mkmlizer to finish
chaiml-llama31-mer-v2-44570-v59-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama31-mer-v2-44570-v59-mkmlizer: bash: no job control in this shell
chaiml-llama31-mer-v2-44570-v59-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-llama31-mer-v2-44570-v59-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ https://mk1.ai ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ belonging to: ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ║ ║
chaiml-llama31-mer-v2-44570-v59-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-mer-v2-44570-v59-mkmlizer: Downloaded to shared memory in 18.188s
chaiml-llama31-mer-v2-44570-v59-mkmlizer: Checking if ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 already exists in ChaiML
chaiml-llama31-mer-v2-44570-v59-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpwje_m7z4, device:0
chaiml-llama31-mer-v2-44570-v59-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama31-mer-v2-44570-v59-mkmlizer:
Loading 0: 0%| | 0.00/291 [00:00<?, ?it/s]
Loading 0: 13%|█▎ | 37.0/291 [00:01<00:07, 35.6it/s]
Loading 0: 13%|█▎ | 37.0/291 [00:01<00:07, 35.6it/s]
Loading 0: 26%|██▋ | 77.0/291 [00:02<00:05, 36.3it/s]
Loading 0: 26%|██▋ | 77.0/291 [00:02<00:05, 36.3it/s]
Loading 0: 37%|███▋ | 107/291 [00:03<00:05, 33.5it/s]
Loading 0: 37%|███▋ | 107/291 [00:03<00:05, 33.5it/s]
Loading 0: 49%|████▉ | 143/291 [00:04<00:04, 34.5it/s]
Loading 0: 49%|████▉ | 143/291 [00:04<00:04, 34.5it/s]
Loading 0: 62%|██████▏ | 179/291 [00:05<00:03, 34.9it/s]
Loading 0: 62%|██████▏ | 179/291 [00:05<00:03, 34.9it/s]
Loading 0: 71%|███████▏ | 208/291 [00:06<00:02, 32.0it/s]
Loading 0: 71%|███████▏ | 208/291 [00:06<00:02, 32.0it/s]
Loading 0: 84%|████████▍ | 244/291 [00:07<00:01, 33.1it/s]
Loading 0: 84%|████████▍ | 244/291 [00:07<00:01, 33.1it/s]
Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 34.0it/s]
Loading 0: 96%|█████████▌| 280/291 [00:08<00:00, 34.0it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00, 31.3it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00, 31.3it/s]
Loading 0: 100%|██████████| 291/291 [00:08<00:00, 33.1it/s]
chaiml-llama31-mer-v2-44570-v59-mkmlizer: quantized model in 20.870s
chaiml-llama31-mer-v2-44570-v59-mkmlizer: Processed model ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 in 39.059s
chaiml-llama31-mer-v2-44570-v59-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-mer-v2-44570-v59-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-mer-v2-44570-v59-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia
chaiml-llama31-mer-v2-44570-v59-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia/config.json
chaiml-llama31-mer-v2-44570-v59-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia/special_tokens_map.json
chaiml-llama31-mer-v2-44570-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia/tokenizer_config.json
chaiml-llama31-mer-v2-44570-v59-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia/tokenizer.json
chaiml-llama31-mer-v2-44570-v59-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-mer-v2-44570-v59/nvidia/flywheel_model.0.safetensors
Job chaiml-llama31-mer-v2-44570-v59-mkmlizer completed after 103.58s with status: succeeded
Stopping job with name chaiml-llama31-mer-v2-44570-v59-mkmlizer
Pipeline stage MKMLizer completed in 104.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama31-mer-v2-44570-v59
Waiting for inference service chaiml-llama31-mer-v2-44570-v59 to be ready
Inference service chaiml-llama31-mer-v2-44570-v59 ready after 150.63764309883118s
Pipeline stage MKMLDeployer completed in 151.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.694502592086792s
Received healthy response to inference request in 4.694915056228638s
Received healthy response to inference request in 3.0000009536743164s
Received healthy response to inference request in 2.564190626144409s
Received healthy response to inference request in 5.199334144592285s
5 requests
0 failed requests
5th percentile: 2.6513526916503904
10th percentile: 2.738514757156372
20th percentile: 2.912838888168335
30th percentile: 3.1389012813568113
40th percentile: 3.4167019367218017
50th percentile: 3.694502592086792
60th percentile: 4.094667577743531
70th percentile: 4.494832563400268
80th percentile: 4.795798873901367
90th percentile: 4.997566509246826
95th percentile: 5.098450326919556
99th percentile: 5.179157381057739
mean time: 3.830588674545288
Pipeline stage StressChecker completed in 20.23s
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 0.59s
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 0.60s
Shutdown handler de-registered
chaiml-llama31-mer-v2-_44570_v59 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 3178.33s
Shutdown handler de-registered
chaiml-llama31-mer-v2-_44570_v59 status is now torndown due to DeploymentManager action