Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer
Waiting for job on chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer to finish
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: bash: no job control in this shell
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ belonging to: ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ║ ║
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: Downloaded to shared memory in 17.391s
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: Checking if ChaiML/prm_kimi_v0_180k_default8b-cosine-lr1e6g16 already exists in ChaiML
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpp1_io5_3, device:0
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer:
Loading 0: 0%| | 0.00/291 [00:00<?, ?it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 40.1it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 40.1it/s]
Loading 0: 28%|██▊ | 82.0/291 [00:02<00:05, 39.5it/s]
Loading 0: 28%|██▊ | 82.0/291 [00:02<00:05, 39.5it/s]
Loading 0: 41%|████ | 118/291 [00:03<00:04, 37.3it/s]
Loading 0: 41%|████ | 118/291 [00:03<00:04, 37.3it/s]
Loading 0: 56%|█████▌ | 163/291 [00:04<00:03, 40.2it/s]
Loading 0: 56%|█████▌ | 163/291 [00:04<00:03, 40.2it/s]
Loading 0: 68%|██████▊ | 198/291 [00:05<00:02, 38.3it/s]
Loading 0: 68%|██████▊ | 198/291 [00:05<00:02, 38.3it/s]
Loading 0: 82%|████████▏ | 239/291 [00:06<00:01, 39.0it/s]
Loading 0: 82%|████████▏ | 239/291 [00:06<00:01, 39.0it/s]
Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 41.3it/s]
Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 41.3it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 37.9it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 37.9it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.9it/s]
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: quantized model in 18.386s
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: Processed model ChaiML/prm_kimi_v0_180k_default8b-cosine-lr1e6g16 in 35.777s
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-prm-kimi-v0-180k-25084-v3/nvidia
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-prm-kimi-v0-180k-25084-v3/nvidia/tokenizer.json
chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-prm-kimi-v0-180k-25084-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer completed after 103.8s with status: succeeded
Stopping job with name chaiml-prm-kimi-v0-180k-25084-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.52s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-prm-kimi-v0-180k-25084-v3
Waiting for inference service chaiml-prm-kimi-v0-180k-25084-v3 to be ready
Inference service chaiml-prm-kimi-v0-180k-25084-v3 ready after 150.96229338645935s
Pipeline stage MKMLDeployer completed in 152.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.222990036010742s
Received healthy response to inference request in 5.0052173137664795s
Received healthy response to inference request in 3.793820858001709s
Received healthy response to inference request in 3.7349908351898193s
Received healthy response to inference request in 1.8415322303771973s
5 requests
0 failed requests
5th percentile: 2.1178237915039064
10th percentile: 2.394115352630615
20th percentile: 2.946698474884033
30th percentile: 3.3253901958465577
40th percentile: 3.5301905155181883
50th percentile: 3.7349908351898193
60th percentile: 3.7585228443145753
70th percentile: 3.7820548534393312
80th percentile: 4.036100149154663
90th percentile: 4.520658731460571
95th percentile: 4.762938022613525
99th percentile: 4.956761455535888
mean time: 3.5197102546691896
Pipeline stage StressChecker completed in 19.04s
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 0.95s
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 1.17s
Shutdown handler de-registered
chaiml-prm-kimi-v0-180k_25084_v3 status is now deployed due to DeploymentManager action
chaiml-prm-kimi-v0-180k_25084_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-prm-kimi-v0-180k_25084_v3 status is now torndown due to DeploymentManager action