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-cai-users-v0-ful-42497-v8-mkmlizer
Waiting for job on chaiml-cai-users-v0-ful-42497-v8-mkmlizer to finish
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Version: 0.30.2 ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ https://mk1.ai ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ belonging to: ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Chai Research Corp. ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ║ ║
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: Downloaded to shared memory in 49.132s
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: Checking if ChaiML/cai-users-v0-full-sft-24b already exists in ChaiML
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp5jpokkqn, device:0
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: quantized model in 284.931s
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: Processed model ChaiML/cai-users-v0-full-sft-24b in 334.064s
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia/config.json
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia/special_tokens_map.json
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia/tokenizer_config.json
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia/tokenizer.json
chaiml-cai-users-v0-ful-42497-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-cai-users-v0-ful-42497-v8/nvidia/flywheel_model.1.safetensors
Job chaiml-cai-users-v0-ful-42497-v8-mkmlizer completed after 413.38s with status: succeeded
Stopping job with name chaiml-cai-users-v0-ful-42497-v8-mkmlizer
Pipeline stage MKMLizer completed in 413.95s
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-cai-users-v0-ful-42497-v8
Waiting for inference service chaiml-cai-users-v0-ful-42497-v8 to be ready
Inference service chaiml-cai-users-v0-ful-42497-v8 ready after 50.78455066680908s
Pipeline stage MKMLDeployer completed in 51.70s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0392274856567383s
Received healthy response to inference request in 1.7229468822479248s
Received healthy response to inference request in 1.9286293983459473s
Received healthy response to inference request in 1.8205442428588867s
Received healthy response to inference request in 1.9708187580108643s
5 requests
0 failed requests
5th percentile: 1.742466354370117
10th percentile: 1.7619858264923096
20th percentile: 1.8010247707366944
30th percentile: 1.842161273956299
40th percentile: 1.885395336151123
50th percentile: 1.9286293983459473
60th percentile: 1.945505142211914
70th percentile: 1.9623808860778809
80th percentile: 1.9845005035400392
90th percentile: 2.0118639945983885
95th percentile: 2.0255457401275634
99th percentile: 2.0364911365509033
mean time: 1.8964333534240723
Pipeline stage StressChecker completed in 10.77s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-cai-users-v0-ful_42497_v8 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-cai-users-v0-ful-42497-v8-profiler
Waiting for inference service chaiml-cai-users-v0-ful-42497-v8-profiler to be ready
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5169.06s
Shutdown handler de-registered
chaiml-cai-users-v0-ful_42497_v8 status is now torndown due to DeploymentManager action