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-4d70-fd43-linear-w02-v3-mkmlizer
Waiting for job on chaiml-4d70-fd43-linear-w02-v3-mkmlizer to finish
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Version: 0.30.2 ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ belonging to: ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ║ ║
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: Downloaded to shared memory in 30.153s
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: Checking if ChaiML/4d70-fd43-linear-w02 already exists in ChaiML
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpruf86iin, device:0
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: quantized model in 144.286s
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: Processed model ChaiML/4d70-fd43-linear-w02 in 174.440s
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia/special_tokens_map.json
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia/config.json
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia/tokenizer_config.json
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia/tokenizer.json
chaiml-4d70-fd43-linear-w02-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-4d70-fd43-linear-w02-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-4d70-fd43-linear-w02-v3-mkmlizer completed after 216.76s with status: succeeded
Stopping job with name chaiml-4d70-fd43-linear-w02-v3-mkmlizer
Pipeline stage MKMLizer completed in 217.28s
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-4d70-fd43-linear-w02-v3
Waiting for inference service chaiml-4d70-fd43-linear-w02-v3 to be ready
Inference service chaiml-4d70-fd43-linear-w02-v3 ready after 70.78683876991272s
Pipeline stage MKMLDeployer completed in 71.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7842612266540527s
Received healthy response to inference request in 1.6781775951385498s
Received healthy response to inference request in 1.5691192150115967s
Received healthy response to inference request in 1.3570637702941895s
Received healthy response to inference request in 1.5309600830078125s
5 requests
0 failed requests
5th percentile: 1.391843032836914
10th percentile: 1.4266222953796386
20th percentile: 1.496180820465088
30th percentile: 1.5385919094085694
40th percentile: 1.553855562210083
50th percentile: 1.5691192150115967
60th percentile: 1.6127425670623778
70th percentile: 1.6563659191131592
80th percentile: 1.6993943214416505
90th percentile: 1.7418277740478516
95th percentile: 1.763044500350952
99th percentile: 1.7800178813934326
mean time: 1.5839163780212402
Pipeline stage StressChecker completed in 9.18s
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 0.65s
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 0.71s
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w02_v3 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
clean up pipeline due to error=DeploymentChecksError('(\'http://chaiml-4d70-fd43-linear-w02-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict\', \'\\n<html><head>\\n<meta http-equiv="content-type" content="text/html;charset=utf-8">\\n<title>502 Server Error</title>\\n</head>\\n<body text=#000000 bgcolor=#ffffff>\\n<h1>Error: Server Error</h1>\\n<h2>The server encountered a temporary error and could not complete your request.<p>Please try again in 30 seconds.</h2>\\n<h2></h2>\\n</body></html>\\n\')')
Shutdown handler de-registered
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
clean up pipeline due to error=DeploymentChecksError("('http://chaiml-4d70-fd43-linear-w02-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')")
Shutdown handler de-registered
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
clean up pipeline due to error=DeploymentChecksError("('http://chaiml-4d70-fd43-linear-w02-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'upstream connect error or disconnect/reset before headers. reset reason: connection timeout')")
Shutdown handler de-registered
chaiml-4d70-fd43-linear-w02_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-4d70-fd43-linear-w02_v3 status is now torndown due to DeploymentManager action