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-llama8brm-nis-2m-89633-v2-mkmlizer
Waiting for job on chaiml-llama8brm-nis-2m-89633-v2-mkmlizer to finish
Failed to get response for submission chaiml-jace-lightwood-s_43552_v2: HTTPConnectionPool(host='chaiml-jace-lightwood-s-43552-v2-predictor.creator-studio.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Version: 0.30.2 ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ belonging to: ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ║ ║
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: Downloaded to shared memory in 35.463s
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: Checking if ChaiML/llama8brm_nis_2Msamp_2048seq_full2m_retune_cos_time_exp2400000 already exists in ChaiML
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpdj09nq8x, device:0
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: quantized model in 15.981s
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: Processed model ChaiML/llama8brm_nis_2Msamp_2048seq_full2m_retune_cos_time_exp2400000 in 51.444s
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia/config.json
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia/special_tokens_map.json
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia/tokenizer_config.json
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia/tokenizer.json
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama8brm-nis-2m-89633-v2/nvidia/flywheel_model.0.safetensors
chaiml-llama8brm-nis-2m-89633-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 35.98it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:05, 51.95it/s]
Loading 0: 8%|▊ | 23/291 [00:00<00:04, 54.89it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:04, 57.27it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:04, 59.12it/s]
Loading 0: 17%|█▋ | 50/291 [00:00<00:03, 60.29it/s]
Loading 0: 20%|██ | 59/291 [00:01<00:03, 60.74it/s]
Loading 0: 23%|██▎ | 68/291 [00:01<00:03, 61.03it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:03, 59.29it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:04, 49.79it/s]
Loading 0: 31%|███ | 89/291 [00:01<00:03, 50.86it/s]
Loading 0: 33%|███▎ | 95/291 [00:01<00:04, 48.46it/s]
Loading 0: 36%|███▌ | 104/291 [00:01<00:03, 52.81it/s]
Loading 0: 39%|███▉ | 113/291 [00:02<00:03, 56.12it/s]
Loading 0: 42%|████▏ | 122/291 [00:02<00:02, 58.44it/s]
Loading 0: 45%|████▌ | 131/291 [00:02<00:02, 59.89it/s]
Loading 0: 48%|████▊ | 140/291 [00:02<00:02, 59.97it/s]
Loading 0: 51%|█████ | 149/291 [00:02<00:02, 60.90it/s]
Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 61.62it/s]
Loading 0: 57%|█████▋ | 167/291 [00:02<00:02, 61.84it/s]
Loading 0: 61%|██████ | 177/291 [00:03<00:01, 64.65it/s]
Loading 0: 64%|██████▎ | 185/291 [00:03<00:01, 67.83it/s]
Loading 0: 66%|██████▌ | 192/291 [00:03<00:02, 48.45it/s]
Loading 0: 68%|██████▊ | 199/291 [00:03<00:01, 49.23it/s]
Loading 0: 70%|███████ | 205/291 [00:03<00:01, 51.21it/s]
Loading 0: 73%|███████▎ | 212/291 [00:03<00:01, 50.58it/s]
Loading 0: 76%|███████▌ | 221/291 [00:03<00:01, 53.98it/s]
Loading 0: 79%|███████▉ | 230/291 [00:04<00:01, 56.57it/s]
Loading 0: 82%|████████▏ | 239/291 [00:04<00:00, 57.99it/s]
Loading 0: 85%|████████▌ | 248/291 [00:04<00:00, 58.94it/s]
Loading 0: 88%|████████▊ | 257/291 [00:04<00:00, 59.65it/s]
Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 64.18it/s]
Loading 0: 93%|█████████▎| 272/291 [00:04<00:00, 62.48it/s]
Loading 0: 96%|█████████▌| 279/291 [00:04<00:00, 63.75it/s]
Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 54.54it/s]
Job chaiml-llama8brm-nis-2m-89633-v2-mkmlizer completed after 114.51s with status: succeeded
Stopping job with name chaiml-llama8brm-nis-2m-89633-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.03s
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 chaiml-llama8brm-nis-2m-89633-v2
Waiting for inference service chaiml-llama8brm-nis-2m-89633-v2 to be ready
Failed to get response for submission chaiml-smallbase-nis-mu_14714_v1: HTTPConnectionPool(host='chaiml-smallbase-nis-mu-14714-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama8brm-nis-2m-89633-v2 ready after 40.21879458427429s
Pipeline stage MKMLDeployer completed in 40.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.067579984664917s
Received healthy response to inference request in 2.775299310684204s
Received healthy response to inference request in 2.518939256668091s
Received healthy response to inference request in 1.9864323139190674s
Failed to get response for submission rirv938-grpo-20250926-c_37256_v2: HTTPConnectionPool(host='rirv938-grpo-20250926-c-37256-v2-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-mn24b-v2preferwi_59255_v8: HTTPConnectionPool(host='chaiml-mn24b-v2preferwi-59255-v8-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 4.357393741607666s
5 requests
0 failed requests
5th percentile: 2.092933702468872
10th percentile: 2.199435091018677
20th percentile: 2.4124378681182863
30th percentile: 2.5702112674713136
40th percentile: 2.6727552890777586
50th percentile: 2.775299310684204
60th percentile: 2.892211580276489
70th percentile: 3.0091238498687742
80th percentile: 3.325542736053467
90th percentile: 3.8414682388305668
95th percentile: 4.099430990219116
99th percentile: 4.305801191329956
mean time: 2.9411289215087892
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 0.68s
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 1.49s
Shutdown handler de-registered
chaiml-llama8brm-nis-2m_89633_v2 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2774.42s
Shutdown handler de-registered
chaiml-llama8brm-nis-2m_89633_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8brm-nis-2m_89633_v2 status is now torndown due to DeploymentManager action