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 junhua024-chai-1-full-002-v21-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v21-mkmlizer to finish
junhua024-chai-1-full-002-v21-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v21-mkmlizer: ║ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Version: 0.29.3 ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ https://mk1.ai ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ The license key for the current software has been verified as ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ belonging to: ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Chai Research Corp. ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
junhua024-chai-1-full-002-v21-mkmlizer: ║ ║
junhua024-chai-1-full-002-v21-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-1-full-002-v21-mkmlizer: Downloaded to shared memory in 81.496s
junhua024-chai-1-full-002-v21-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v21-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_6_wsbm8, device:0
junhua024-chai-1-full-002-v21-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v21-mkmlizer: quantized model in 37.143s
junhua024-chai-1-full-002-v21-mkmlizer: Processed model junhua024/chai_1-full_002 in 118.774s
junhua024-chai-1-full-002-v21-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v21-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v21-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21
junhua024-chai-1-full-002-v21-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21/special_tokens_map.json
junhua024-chai-1-full-002-v21-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21/config.json
junhua024-chai-1-full-002-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21/tokenizer_config.json
junhua024-chai-1-full-002-v21-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21/tokenizer.json
junhua024-chai-1-full-002-v21-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v21/flywheel_model.0.safetensors
Job junhua024-chai-1-full-002-v21-mkmlizer completed after 147.91s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v21-mkmlizer
Pipeline stage MKMLizer completed in 148.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-002-v21
Waiting for inference service junhua024-chai-1-full-002-v21 to be ready
Inference service junhua024-chai-1-full-002-v21 ready after 181.0776023864746s
Pipeline stage MKMLDeployer completed in 182.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5930798053741455s
Received healthy response to inference request in 1.5825908184051514s
Received healthy response to inference request in 1.5733537673950195s
Received healthy response to inference request in 1.6386473178863525s
Received healthy response to inference request in 1.6966185569763184s
5 requests
0 failed requests
5th percentile: 1.5752011775970458
10th percentile: 1.5770485877990723
20th percentile: 1.580743408203125
30th percentile: 1.5938021183013915
40th percentile: 1.616224718093872
50th percentile: 1.6386473178863525
60th percentile: 1.6618358135223388
70th percentile: 1.6850243091583252
80th percentile: 1.875910806655884
90th percentile: 2.2344953060150146
95th percentile: 2.41378755569458
99th percentile: 2.5572213554382324
mean time: 1.8168580532073975
Pipeline stage StressChecker completed in 10.52s
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 0.90s
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 0.69s
Shutdown handler de-registered
junhua024-chai-1-full-002_v21 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5531.47s
Shutdown handler de-registered
junhua024-chai-1-full-002_v21 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v21 status is now torndown due to DeploymentManager action