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-02-full-0121-v1-mkmlizer
Waiting for job on junhua024-chai-02-full-0121-v1-mkmlizer to finish
junhua024-chai-02-full-0121-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Version: 0.29.15 ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ https://mk1.ai ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ The license key for the current software has been verified as ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ belonging to: ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Chai Research Corp. ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
junhua024-chai-02-full-0121-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0121-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-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-02-full-0121-v1-mkmlizer: Downloaded to shared memory in 146.018s
junhua024-chai-02-full-0121-v1-mkmlizer: Checking if junhua024/chai_02_full_0121 already exists in ChaiML
junhua024-chai-02-full-0121-v1-mkmlizer: Creating repo ChaiML/chai_02_full_0121 and uploading /tmp/tmpr4lflebd to it
junhua024-chai-02-full-0121-v1-mkmlizer:
0%| | 0/26 [00:00<?, ?it/s]
4%|▍ | 1/26 [00:01<00:45, 1.82s/it]
8%|▊ | 2/26 [00:03<00:42, 1.77s/it]
12%|█▏ | 3/26 [00:05<00:38, 1.66s/it]
15%|█▌ | 4/26 [00:06<00:38, 1.75s/it]
19%|█▉ | 5/26 [00:08<00:36, 1.73s/it]
23%|██▎ | 6/26 [00:11<00:40, 2.05s/it]
27%|██▋ | 7/26 [00:13<00:38, 2.02s/it]
31%|███ | 8/26 [00:15<00:35, 1.98s/it]
35%|███▍ | 9/26 [00:17<00:34, 2.06s/it]
38%|███▊ | 10/26 [00:19<00:32, 2.03s/it]
42%|████▏ | 11/26 [00:21<00:29, 1.98s/it]
46%|████▌ | 12/26 [00:23<00:27, 1.94s/it]
50%|█████ | 13/26 [00:26<00:31, 2.41s/it]
54%|█████▍ | 14/26 [00:28<00:28, 2.41s/it]
58%|█████▊ | 15/26 [00:30<00:24, 2.22s/it]
62%|██████▏ | 16/26 [00:32<00:19, 2.00s/it]
65%|██████▌ | 17/26 [00:38<00:29, 3.26s/it]
69%|██████▉ | 18/26 [00:40<00:22, 2.79s/it]
73%|███████▎ | 19/26 [00:41<00:17, 2.49s/it]
77%|███████▋ | 20/26 [00:46<00:19, 3.17s/it]
81%|████████ | 21/26 [00:48<00:14, 2.87s/it]
85%|████████▍ | 22/26 [00:50<00:10, 2.60s/it]
88%|████████▊ | 23/26 [00:56<00:10, 3.64s/it]
92%|█████████▏| 24/26 [01:00<00:06, 3.48s/it]
96%|█████████▌| 25/26 [01:06<00:04, 4.27s/it]
100%|██████████| 26/26 [01:07<00:00, 3.43s/it]
100%|██████████| 26/26 [01:07<00:00, 2.60s/it]
junhua024-chai-02-full-0121-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr4lflebd, device:0
junhua024-chai-02-full-0121-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-0121-v1-mkmlizer: quantized model in 30.854s
junhua024-chai-02-full-0121-v1-mkmlizer: Processed model junhua024/chai_02_full_0121 in 270.844s
junhua024-chai-02-full-0121-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-0121-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-0121-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia
junhua024-chai-02-full-0121-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia/config.json
junhua024-chai-02-full-0121-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia/special_tokens_map.json
junhua024-chai-02-full-0121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia/tokenizer_config.json
junhua024-chai-02-full-0121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia/tokenizer.json
junhua024-chai-02-full-0121-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-0121-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-0121-v1-mkmlizer:
Loading 0: 0%| | 0/363 [00:00<?, ?it/s]
Loading 0: 1%| | 2/363 [00:00<00:23, 15.27it/s]
Loading 0: 1%|▏ | 5/363 [00:00<00:21, 16.91it/s]
Loading 0: 3%|▎ | 12/363 [00:00<00:12, 28.36it/s]
Loading 0: 5%|▍ | 17/363 [00:00<00:11, 30.68it/s]
Loading 0: 6%|▋ | 23/363 [00:00<00:10, 33.12it/s]
Loading 0: 9%|▉ | 32/363 [00:00<00:07, 46.86it/s]
Loading 0: 10%|█ | 38/363 [00:01<00:08, 36.58it/s]
Loading 0: 12%|█▏ | 43/363 [00:01<00:08, 36.41it/s]
Loading 0: 13%|█▎ | 49/363 [00:01<00:07, 41.29it/s]
Loading 0: 15%|█▍ | 54/363 [00:01<00:09, 30.94it/s]
Loading 0: 16%|█▋ | 59/363 [00:01<00:09, 33.08it/s]
Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.41it/s]
Loading 0: 19%|█▉ | 69/363 [00:02<00:09, 31.80it/s]
Loading 0: 20%|██ | 74/363 [00:02<00:08, 34.15it/s]
Loading 0: 21%|██▏ | 78/363 [00:02<00:08, 33.67it/s]
Loading 0: 23%|██▎ | 82/363 [00:02<00:09, 28.16it/s]
Loading 0: 24%|██▎ | 86/363 [00:02<00:09, 29.04it/s]
Loading 0: 25%|██▌ | 91/363 [00:02<00:08, 30.49it/s]
Loading 0: 27%|██▋ | 97/363 [00:02<00:08, 33.09it/s]
Loading 0: 28%|██▊ | 101/363 [00:03<00:07, 33.57it/s]
Loading 0: 29%|██▉ | 105/363 [00:03<00:08, 31.47it/s]
Loading 0: 31%|███ | 113/363 [00:03<00:06, 38.73it/s]
Loading 0: 32%|███▏ | 117/363 [00:03<00:07, 31.29it/s]
Loading 0: 34%|███▎ | 122/363 [00:03<00:07, 32.24it/s]
Loading 0: 35%|███▌ | 128/363 [00:03<00:06, 34.10it/s]
Loading 0: 36%|███▋ | 132/363 [00:04<00:07, 32.51it/s]
Loading 0: 38%|███▊ | 138/363 [00:04<00:06, 32.66it/s]
Loading 0: 39%|███▉ | 143/363 [00:04<00:06, 33.01it/s]
Loading 0: 41%|████ | 149/363 [00:04<00:06, 34.46it/s]
Loading 0: 43%|████▎ | 155/363 [00:04<00:05, 39.62it/s]
Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 37.93it/s]
Loading 0: 45%|████▌ | 164/363 [00:04<00:05, 36.54it/s]
Loading 0: 46%|████▋ | 168/363 [00:05<00:05, 33.09it/s]
Loading 0: 48%|████▊ | 176/363 [00:05<00:04, 39.48it/s]
Loading 0: 50%|████▉ | 180/363 [00:05<00:05, 31.74it/s]
Loading 0: 51%|█████ | 185/363 [00:05<00:05, 34.15it/s]
Loading 0: 53%|█████▎ | 191/363 [00:05<00:04, 36.37it/s]
Loading 0: 54%|█████▎ | 195/363 [00:05<00:04, 34.68it/s]
Loading 0: 55%|█████▌ | 201/363 [00:05<00:04, 34.98it/s]
Loading 0: 57%|█████▋ | 206/363 [00:06<00:04, 35.05it/s]
Loading 0: 58%|█████▊ | 212/363 [00:06<00:04, 35.29it/s]
Loading 0: 61%|██████ | 220/363 [00:06<00:03, 44.44it/s]
Loading 0: 62%|██████▏ | 225/363 [00:06<00:04, 34.46it/s]
Loading 0: 63%|██████▎ | 230/363 [00:06<00:03, 33.81it/s]
Loading 0: 66%|██████▌ | 239/363 [00:06<00:03, 40.99it/s]
Loading 0: 67%|██████▋ | 244/363 [00:07<00:03, 33.44it/s]
Loading 0: 68%|██████▊ | 248/363 [00:07<00:03, 32.40it/s]
Loading 0: 70%|██████▉ | 254/363 [00:07<00:03, 34.46it/s]
Loading 0: 71%|███████ | 258/363 [00:07<00:03, 33.72it/s]
Loading 0: 73%|███████▎ | 264/363 [00:07<00:02, 34.68it/s]
Loading 0: 74%|███████▍ | 269/363 [00:07<00:02, 34.46it/s]
Loading 0: 76%|███████▌ | 275/363 [00:08<00:02, 35.47it/s]
Loading 0: 78%|███████▊ | 283/363 [00:08<00:01, 44.56it/s]
Loading 0: 79%|███████▉ | 288/363 [00:08<00:02, 34.36it/s]
Loading 0: 81%|████████ | 293/363 [00:08<00:01, 35.26it/s]
Loading 0: 83%|████████▎ | 302/363 [00:08<00:01, 43.26it/s]
Loading 0: 85%|████████▍ | 307/363 [00:08<00:01, 36.96it/s]
Loading 0: 86%|████████▌ | 312/363 [00:08<00:01, 37.06it/s]
Loading 0: 87%|████████▋ | 317/363 [00:09<00:01, 36.57it/s]
Loading 0: 88%|████████▊ | 321/363 [00:09<00:01, 34.78it/s]
Loading 0: 90%|████████▉ | 326/363 [00:09<00:01, 36.72it/s]
Loading 0: 91%|█████████ | 330/363 [00:09<00:00, 37.33it/s]
Loading 0: 92%|█████████▏| 334/363 [00:09<00:00, 33.40it/s]
Loading 0: 93%|█████████▎| 338/363 [00:09<00:00, 31.90it/s]
Loading 0: 95%|█████████▌| 346/363 [00:09<00:00, 42.78it/s]
Loading 0: 97%|█████████▋| 351/363 [00:10<00:00, 23.73it/s]
Loading 0: 98%|█████████▊| 355/363 [00:10<00:00, 26.13it/s]
Loading 0: 99%|█████████▉| 359/363 [00:10<00:00, 28.38it/s]
Job junhua024-chai-02-full-0121-v1-mkmlizer completed after 296.44s with status: succeeded
Stopping job with name junhua024-chai-02-full-0121-v1-mkmlizer
Pipeline stage MKMLizer completed in 296.96s
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-02-full-0121-v1
Waiting for inference service junhua024-chai-02-full-0121-v1 to be ready
Inference service junhua024-chai-02-full-0121-v1 ready after 261.60565519332886s
Pipeline stage MKMLDeployer completed in 262.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.654743194580078s
Received healthy response to inference request in 1.6061670780181885s
Received healthy response to inference request in 2.190484046936035s
Received healthy response to inference request in 2.6586854457855225s
Received healthy response to inference request in 1.8450093269348145s
5 requests
0 failed requests
5th percentile: 1.6539355278015138
10th percentile: 1.7017039775848388
20th percentile: 1.7972408771514892
30th percentile: 1.9141042709350586
40th percentile: 2.052294158935547
50th percentile: 2.190484046936035
60th percentile: 2.3761877059936523
70th percentile: 2.5618913650512694
80th percentile: 2.655531644821167
90th percentile: 2.6571085453033447
95th percentile: 2.6578969955444336
99th percentile: 2.6585277557373046
mean time: 2.191017818450928
Pipeline stage StressChecker completed in 12.34s
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 0.73s
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 0.67s
Shutdown handler de-registered
junhua024-chai-02-full-0121_v1 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 3231.79s
Shutdown handler de-registered
junhua024-chai-02-full-0121_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-0121_v1 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-0121_v1 status is now torndown due to DeploymentManager action