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-202503-16869-v39-mkmlizer
Waiting for job on chaiml-llama-8b-202503-16869-v39-mkmlizer to finish
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-live-rm-20260216-8340-v3-mkmlizer
Waiting for job on chaiml-live-rm-20260216-8340-v3-mkmlizer to finish
chaiml-llama-8b-202503-16869-v39-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-llama-8b-202503-16869-v39-mkmlizer: bash: no job control in this shell
chaiml-llama-8b-202503-16869-v39-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-llama-8b-202503-16869-v39-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-llama-8b-202503-16869-v39-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-202503-16869-v39-mkmlizer: Downloaded to shared memory in 15.985s
chaiml-llama-8b-202503-16869-v39-mkmlizer: Checking if ChaiML/llama_8b_202503_1m_nemo_safety already exists in ChaiML
chaiml-llama-8b-202503-16869-v39-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpt_tge91d, device:0
chaiml-llama-8b-202503-16869-v39-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-live-rm-20260216-8340-v3-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-live-rm-20260216-8340-v3-mkmlizer: bash: no job control in this shell
chaiml-llama-8b-202503-16869-v39-mkmlizer:
Loading 0: 0%| | 0.00/291 [00:00<?, ?it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 39.9it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 39.9it/s]
Loading 0: 29%|██▊ | 83.0/291 [00:02<00:05, 37.3it/s]
Loading 0: 29%|██▊ | 83.0/291 [00:02<00:05, 37.3it/s]
Loading 0: 43%|████▎ | 125/291 [00:03<00:04, 39.3it/s]
Loading 0: 43%|████▎ | 125/291 [00:03<00:04, 39.3it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 39.4it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 39.4it/s]
Loading 0: 70%|██████▉ | 203/291 [00:05<00:02, 37.8it/s]
Loading 0: 70%|██████▉ | 203/291 [00:05<00:02, 37.8it/s]
Loading 0: 85%|████████▌ | 248/291 [00:06<00:01, 39.0it/s]
Loading 0: 85%|████████▌ | 248/291 [00:06<00:01, 39.0it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 38.1it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 38.1it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.0it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.0it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.4it/s]
chaiml-live-rm-20260216-8340-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-live-rm-20260216-8340-v3-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-live-rm-20260216-8340-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: quantized model in 18.503s
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: Processed model ChaiML/llama_8b_202503_1m_nemo_safety in 34.488s
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: creating bucket guanaco-mkml-models
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia/config.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia/special_tokens_map.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia/tokenizer_config.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-202503-16869-v39-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia/tokenizer.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ belonging to: ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ║ ║
chaiml-live-rm-20260216-8340-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-live-rm-20260216-8340-v3-mkmlizer:
Loading 0: 0%| | 0.00/291 [00:00<?, ?it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 38.8it/s]
Loading 0: 14%|█▍ | 41.0/291 [00:01<00:06, 38.8it/s]
Loading 0: 29%|██▊ | 83.0/291 [00:02<00:05, 37.6it/s]
Loading 0: 29%|██▊ | 83.0/291 [00:02<00:05, 37.6it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 39.1it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 39.1it/s]
Loading 0: 59%|█████▉ | 172/291 [00:04<00:02, 40.2it/s]
Loading 0: 59%|█████▉ | 172/291 [00:04<00:02, 40.2it/s]
Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 38.2it/s]
Loading 0: 71%|███████▏ | 208/291 [00:05<00:02, 38.2it/s]
Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 39.7it/s]
Loading 0: 87%|████████▋ | 253/291 [00:06<00:00, 39.7it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 37.9it/s]
Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 37.9it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 37.8it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 37.8it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 38.5it/s]
chaiml-live-rm-20260216-8340-v3-mkmlizer: quantized model in 18.584s
chaiml-live-rm-20260216-8340-v3-mkmlizer: Processed model ChaiML/live_rm_20260216_1024_cp390_from_prev in 34.608s
chaiml-live-rm-20260216-8340-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-live-rm-20260216-8340-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-live-rm-20260216-8340-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v3/nvidia
chaiml-live-rm-20260216-8340-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v3/nvidia/config.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v3/nvidia/special_tokens_map.json
chaiml-live-rm-20260216-8340-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v3/nvidia/tokenizer_config.json
chaiml-llama-8b-202503-16869-v39-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-202503-16869-v39/nvidia/flywheel_model.0.safetensors
Job chaiml-llama-8b-202503-16869-v39-mkmlizer completed after 114.74s with status: succeeded
Stopping job with name chaiml-llama-8b-202503-16869-v39-mkmlizer
Pipeline stage MKMLizer completed in 116.04s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-202503-16869-v39
Waiting for inference service chaiml-llama-8b-202503-16869-v39 to be ready
chaiml-live-rm-20260216-8340-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-live-rm-20260216-8340-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-live-rm-20260216-8340-v3-mkmlizer completed after 136.55s with status: succeeded
Stopping job with name chaiml-live-rm-20260216-8340-v3-mkmlizer
Pipeline stage MKMLizer completed in 138.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-live-rm-20260216-8340-v3
Waiting for inference service chaiml-live-rm-20260216-8340-v3 to be ready
Inference service chaiml-llama-8b-202503-16869-v39 ready after 162.168803691864s
Pipeline stage MKMLDeployer completed in 163.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.8819899559021s
Received healthy response to inference request in 6.602936267852783s
Received healthy response to inference request in 5.837939739227295s
Inference service chaiml-live-rm-20260216-8340-v3 ready after 162.06209516525269s
Pipeline stage MKMLDeployer completed in 163.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.5939202308654785s
Received healthy response to inference request in 4.375032186508179s
Received healthy response to inference request in 5.66740345954895s
5 requests
0 failed requests
5th percentile: 5.701510715484619
10th percentile: 5.735617971420288
20th percentile: 5.803832483291626
30th percentile: 5.989135837554931
40th percentile: 6.291528034210205
50th percentile: 6.5939202308654785
Received healthy response to inference request in 4.539682388305664s
60th percentile: 6.5975266456604
70th percentile: 6.601133060455322
80th percentile: 6.658747005462646
90th percentile: 6.770368480682373
95th percentile: 6.8261792182922365
99th percentile: 6.870827808380127
mean time: 6.316837930679322
%s, retrying in %s seconds...
Received healthy response to inference request in 5.256105184555054s
Received healthy response to inference request in 6.5545172691345215s
Received healthy response to inference request in 6.129997968673706s
Received healthy response to inference request in 5.1123504638671875s
Received healthy response to inference request in 6.557272434234619s
5 requests
0 failed requests
5th percentile: 4.407962226867676
10th percentile: 4.440892267227173
20th percentile: 4.506752347946167
30th percentile: 4.682966947555542
40th percentile: 4.969536066055298
50th percentile: 5.256105184555054
Received healthy response to inference request in 5.978997230529785s
60th percentile: 5.605662298202515
70th percentile: 5.955219411849975
80th percentile: 6.215452861785889
90th percentile: 6.3863626480102536
95th percentile: 6.471817541122436
99th percentile: 6.540181455612182
mean time: 5.371618032455444
Pipeline stage StressChecker completed in 32.93s
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 2.31s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
Received healthy response to inference request in 5.869185209274292s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.24s
Shutdown handler de-registered
chaiml-live-rm-20260216-_8340_v3 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 5.8492913246154785s
5 requests
0 failed requests
5th percentile: 5.259738636016846
10th percentile: 5.407126808166504
20th percentile: 5.70190315246582
30th percentile: 5.853270101547241
40th percentile: 5.861227655410767
50th percentile: 5.869185209274292
60th percentile: 5.913110017776489
70th percentile: 5.9570348262786865
80th percentile: 6.094101238250732
90th percentile: 6.324309253692627
95th percentile: 6.439413261413574
99th percentile: 6.531496467590332
mean time: 5.872868299484253
Pipeline stage StressChecker completed in 71.34s
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 1.35s
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 1.23s
Shutdown handler de-registered
chaiml-llama-8b-202503_16869_v39 status is now deployed due to DeploymentManager action