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-20250611-retune-50947-v1-mkmlizer
Waiting for job on chaiml-20250611-retune-50947-v1-mkmlizer to finish
chaiml-20250611-retune-50947-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Version: 0.27.1+vampire_v3 ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ belonging to: ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-20250611-retune-50947-v1-mkmlizer: ║ ║
chaiml-20250611-retune-50947-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250611-retune-50947-v1-mkmlizer: Downloaded to shared memory in 74.761s
chaiml-20250611-retune-50947-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpa9o2j919, device:0
chaiml-20250611-retune-50947-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250611-retune-50947-v1-mkmlizer: quantized model in 19.367s
chaiml-20250611-retune-50947-v1-mkmlizer: Processed model ChaiML/20250611_retune_long_user_messages in 94.129s
chaiml-20250611-retune-50947-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250611-retune-50947-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250611-retune-50947-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1
chaiml-20250611-retune-50947-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1/config.json
chaiml-20250611-retune-50947-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1/special_tokens_map.json
chaiml-20250611-retune-50947-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1/tokenizer_config.json
chaiml-20250611-retune-50947-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1/tokenizer.json
chaiml-20250611-retune-50947-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-20250611-retune-50947-v1/flywheel_model.0.safetensors
chaiml-20250611-retune-50947-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.61it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 50.98it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:06, 44.62it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 43.27it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 49.60it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 45.02it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 43.65it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 48.91it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 45.22it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.99it/s]
Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 46.55it/s]
Loading 0: 24%|██▍ | 71/291 [00:01<00:04, 45.98it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 45.92it/s]
Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 43.13it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 28.46it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:05, 35.38it/s]
Loading 0: 34%|███▍ | 99/291 [00:02<00:05, 38.27it/s]
Loading 0: 36%|███▌ | 104/291 [00:02<00:05, 33.77it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 42.37it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:04, 41.39it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:04, 41.55it/s]
Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 46.61it/s]
Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 42.96it/s]
Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 42.42it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 47.18it/s]
Loading 0: 53%|█████▎ | 154/291 [00:03<00:03, 43.65it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:03, 42.98it/s]
Loading 0: 57%|█████▋ | 165/291 [00:03<00:02, 46.54it/s]
Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 46.08it/s]
Loading 0: 60%|██████ | 175/291 [00:04<00:02, 46.58it/s]
Loading 0: 62%|██████▏ | 180/291 [00:04<00:02, 45.60it/s]
Loading 0: 64%|██████▍ | 186/291 [00:04<00:02, 42.61it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 29.23it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:03, 30.33it/s]
Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 37.89it/s]
Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 38.17it/s]
Loading 0: 73%|███████▎ | 213/291 [00:05<00:02, 38.11it/s]
Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 43.09it/s]
Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 44.02it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 44.58it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 42.40it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 42.39it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.85it/s]
Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 44.52it/s]
Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 44.13it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 48.95it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 45.23it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 43.26it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 39.63it/s]
Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 30.86it/s]
Job chaiml-20250611-retune-50947-v1-mkmlizer completed after 148.62s with status: succeeded
Stopping job with name chaiml-20250611-retune-50947-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-20250611-retune-50947-v1
Waiting for inference service chaiml-20250611-retune-50947-v1 to be ready
Inference service chaiml-20250611-retune-50947-v1 ready after 110.45607590675354s
Pipeline stage MKMLDeployer completed in 111.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3592913150787354s
Received healthy response to inference request in 2.7831079959869385s
Received healthy response to inference request in 2.6098508834838867s
Received healthy response to inference request in 2.3148562908172607s
Received healthy response to inference request in 2.51189923286438s
5 requests
0 failed requests
5th percentile: 2.3542648792266845
10th percentile: 2.393673467636108
20th percentile: 2.472490644454956
30th percentile: 2.5314895629882814
40th percentile: 2.570670223236084
50th percentile: 2.6098508834838867
60th percentile: 2.6791537284851072
70th percentile: 2.748456573486328
80th percentile: 2.8983446598052978
90th percentile: 3.128817987442017
95th percentile: 3.244054651260376
99th percentile: 3.3362439823150636
mean time: 2.71580114364624
Pipeline stage StressChecker completed in 15.92s
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 0.93s
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 0.75s
Shutdown handler de-registered
chaiml-20250611-retune-_50947_v1 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-50947-v1-profiler
Waiting for inference service chaiml-20250611-retune-50947-v1-profiler to be ready
Inference service chaiml-20250611-retune-50947-v1-profiler ready after 110.71306896209717s
Pipeline stage MKMLProfilerDeployer completed in 111.26s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh:/code/chaiverse_profiler_1749687508 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687508 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687508/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh:/code/chaiverse_profiler_1749687513 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687513 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687513/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh:/code/chaiverse_profiler_1749687517 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplonzkqh --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687517 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687517/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1749687517/profiles.py", line 23, in <module>\n from guanaco_model_service.config import ADMIN_KEY\nModuleNotFoundError: No module named \'guanaco_model_service\'\ncommand terminated with exit code 1\n, output: ')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-20250611-retune-50947-v1-profiler is running
Tearing down inference service chaiml-20250611-retune-50947-v1-profiler
Service chaiml-20250611-retune-50947-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.88s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-20250611-retune-50947-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-50947-v1-profiler
Waiting for inference service chaiml-20250611-retune-50947-v1-profiler to be ready
Inference service chaiml-20250611-retune-50947-v1-profiler ready after 100.6397111415863s
Pipeline stage MKMLProfilerDeployer completed in 101.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6:/code/chaiverse_profiler_1749687689 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687689 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687689/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6:/code/chaiverse_profiler_1749687694 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687694 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687694/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6:/code/chaiverse_profiler_1749687698 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retuf10bb2bb8c2ec28e1319d8ca3c6d272d-deplohtbt6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1749687698 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1749687698/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1749687698/profiles.py", line 23, in <module>\n from guanaco_model_service.config import ADMIN_KEY\nModuleNotFoundError: No module named \'guanaco_model_service\'\ncommand terminated with exit code 1\n, output: ')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-20250611-retune-50947-v1-profiler is running
Tearing down inference service chaiml-20250611-retune-50947-v1-profiler
Service chaiml-20250611-retune-50947-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 6735.12s
Shutdown handler de-registered
chaiml-20250611-retune-_50947_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250611-retune-_50947_v1 status is now torndown due to DeploymentManager action