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-multih-78780-v16-mkmlizer
Waiting for job on chaiml-llama-8b-multih-78780-v16-mkmlizer to finish
chaiml-llama-8b-multih-78780-v16-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multih-78780-v16-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-multih-78780-v16-mkmlizer: Downloaded to shared memory in 38.562s
chaiml-llama-8b-multih-78780-v16-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmporf_54mp, device:0
chaiml-llama-8b-multih-78780-v16-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-multih-78780-v16-mkmlizer: quantized model in 19.616s
chaiml-llama-8b-multih-78780-v16-mkmlizer: Processed model ChaiML/llama_8b_multihead_204m_512_v3_tokens_step_398208 in 58.179s
chaiml-llama-8b-multih-78780-v16-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multih-78780-v16-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multih-78780-v16-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16
chaiml-llama-8b-multih-78780-v16-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16/config.json
chaiml-llama-8b-multih-78780-v16-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16/special_tokens_map.json
chaiml-llama-8b-multih-78780-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16/tokenizer_config.json
chaiml-llama-8b-multih-78780-v16-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16/tokenizer.json
chaiml-llama-8b-multih-78780-v16-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multih-78780-v16/flywheel_model.0.safetensors
Job chaiml-llama-8b-multih-78780-v16-mkmlizer completed after 216.14s with status: succeeded
Stopping job with name chaiml-llama-8b-multih-78780-v16-mkmlizer
Pipeline stage MKMLizer completed in 216.66s
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-llama-8b-multih-78780-v16
Waiting for inference service chaiml-llama-8b-multih-78780-v16 to be ready
Inference service chaiml-llama-8b-multih-78780-v16 ready after 221.0852677822113s
Pipeline stage MKMLDeployer completed in 221.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.132497072219849s
Received healthy response to inference request in 4.050187587738037s
Received healthy response to inference request in 2.8619940280914307s
Received healthy response to inference request in 2.263223171234131s
Received healthy response to inference request in 3.4544856548309326s
5 requests
0 failed requests
5th percentile: 2.382977342605591
10th percentile: 2.502731513977051
20th percentile: 2.7422398567199706
30th percentile: 2.980492353439331
40th percentile: 3.217489004135132
50th percentile: 3.4544856548309326
60th percentile: 3.6927664279937744
70th percentile: 3.931047201156616
80th percentile: 4.066649484634399
90th percentile: 4.099573278427124
95th percentile: 4.1160351753234865
99th percentile: 4.129204692840577
mean time: 3.352477502822876
%s, retrying in %s seconds...
Received healthy response to inference request in 2.9893388748168945s
Received healthy response to inference request in 4.066971302032471s
Received healthy response to inference request in 3.2417993545532227s
Received healthy response to inference request in 2.130610227584839s
Received healthy response to inference request in 2.7543277740478516s
5 requests
0 failed requests
5th percentile: 2.2553537368774412
10th percentile: 2.380097246170044
20th percentile: 2.629584264755249
30th percentile: 2.80132999420166
40th percentile: 2.8953344345092775
50th percentile: 2.9893388748168945
60th percentile: 3.090323066711426
70th percentile: 3.191307258605957
80th percentile: 3.4068337440490724
90th percentile: 3.7369025230407718
95th percentile: 3.901936912536621
99th percentile: 4.033964424133301
mean time: 3.0366095066070558
Pipeline stage StressChecker completed in 34.32s
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 0.65s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v16 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multih-78780-v16-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v16-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
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v16-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.33s
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-llama-8b-multih-78780-v16-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v16-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v16-profiler ready after 110.45537996292114s
Pipeline stage MKMLProfilerDeployer completed in 110.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult1794c518f0ac539e599a63f894e9ce88-deplobgb4t:/code/chaiverse_profiler_1739389509 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult1794c518f0ac539e599a63f894e9ce88-deplobgb4t --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739389509 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1739389509/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v16-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v16-profiler
Service chaiml-llama-8b-multih-78780-v16-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.61s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v16-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.55s
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-llama-8b-multih-78780-v16-profiler
Waiting for inference service chaiml-llama-8b-multih-78780-v16-profiler to be ready
Inference service chaiml-llama-8b-multih-78780-v16-profiler ready after 70.31758141517639s
Pipeline stage MKMLProfilerDeployer completed in 70.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult1794c518f0ac539e599a63f894e9ce88-deplockcws:/code/chaiverse_profiler_1739393108 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult1794c518f0ac539e599a63f894e9ce88-deplockcws --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1739393108 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1739393108/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multih-78780-v16-profiler is running
Tearing down inference service chaiml-llama-8b-multih-78780-v16-profiler
Service chaiml-llama-8b-multih-78780-v16-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.28s
Shutdown handler de-registered
chaiml-llama-8b-multih_78780_v16 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-multih_78780_v16 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v16 status is now torndown due to DeploymentManager action
chaiml-llama-8b-multih_78780_v16 status is now torndown due to DeploymentManager action