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 rirv938-llama-8b-scaleup-400k-v4-mkmlizer
2 validation errors for MultiheadRewardSubmission
platform
unexpected value; permitted: 'multihead_reward' (type=value_error.const; given=reward; permitted=('multihead_reward',))
weights
field required (type=value_error.missing)
Waiting for job on rirv938-llama-8b-scaleup-400k-v4-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 rirv938-llama-8b-scaleup-200k-v2-mkmlizer
Waiting for job on rirv938-llama-8b-scaleup-200k-v2-mkmlizer to finish
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Version: 0.25.10 ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Version: 0.25.10 ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ║ ║
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: Downloaded to shared memory in 22.219s
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpkastl4tg, device:0
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: Downloaded to shared memory in 37.466s
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpet99n9yg, device:0
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: quantized model in 19.232s
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: Processed model rirv938/llama_8b_scaleup_200k in 41.451s
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2/config.json
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2/special_tokens_map.json
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2/tokenizer_config.json
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2/tokenizer.json
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: quantized model in 19.762s
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: Processed model rirv938/llama_8b_scaleup_400k in 57.228s
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-scaleup-200k-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-200k-v2/flywheel_model.0.safetensors
rirv938-llama-8b-scaleup-200k-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.23it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.26it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 46.97it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:05, 48.72it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:04, 52.09it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 48.31it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:04, 50.15it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 51.94it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 46.49it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 46.19it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 52.01it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 48.52it/s]
Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 48.66it/s]
Loading 0: 29%|██▉ | 84/291 [00:01<00:05, 35.02it/s]
Loading 0: 31%|███ | 89/291 [00:01<00:05, 37.61it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 39.87it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 39.37it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 40.47it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 47.42it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:03, 43.97it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 42.55it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 48.50it/s]
Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 44.00it/s]
Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 43.91it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:02, 49.72it/s]
Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 47.28it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 46.25it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 50.10it/s]
Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.02it/s]
Loading 0: 61%|██████ | 177/291 [00:03<00:02, 45.57it/s]
Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 43.40it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 32.92it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 33.49it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:02, 32.57it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 37.89it/s]
Loading 0: 71%|███████ | 206/291 [00:04<00:02, 38.72it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 40.04it/s]
Loading 0: 74%|███████▍ | 216/291 [00:04<00:01, 41.91it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 36.36it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 45.83it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 43.43it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 41.83it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 47.61it/s]
Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 43.38it/s]
Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 41.60it/s]
Loading 0: 91%|█████████ | 264/291 [00:06<00:00, 44.52it/s]
Loading 0: 92%|█████████▏| 269/291 [00:06<00:00, 43.56it/s]
Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 42.50it/s]
Loading 0: 96%|█████████▌| 279/291 [00:06<00:00, 43.14it/s]
Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 35.20it/s]
Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 25.70it/s]
Job rirv938-llama-8b-scaleup-200k-v2-mkmlizer completed after 69.41s with status: succeeded
Stopping job with name rirv938-llama-8b-scaleup-200k-v2-mkmlizer
Pipeline stage MKMLizer completed in 70.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.38s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-scaleup-200k-v2
Waiting for inference service rirv938-llama-8b-scaleup-200k-v2 to be ready
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-400k-v4/config.json
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-400k-v4/special_tokens_map.json
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-400k-v4/tokenizer_config.json
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-400k-v4/tokenizer.json
rirv938-llama-8b-scaleup-400k-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-scaleup-400k-v4/flywheel_model.0.safetensors
rirv938-llama-8b-scaleup-400k-v4-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:08, 34.42it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:05, 50.85it/s]
Loading 0: 6%|▌ | 18/291 [00:00<00:05, 50.10it/s]
Loading 0: 8%|▊ | 24/291 [00:00<00:06, 44.37it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 51.55it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 49.43it/s]
Loading 0: 15%|█▍ | 43/291 [00:00<00:04, 50.77it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 53.08it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 46.61it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.67it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 48.26it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 44.20it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 43.61it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 32.77it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 31.85it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 36.77it/s]
Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 37.53it/s]
Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 39.08it/s]
Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 41.68it/s]
Loading 0: 39%|███▉ | 113/291 [00:02<00:05, 35.17it/s]
Loading 0: 41%|████ | 120/291 [00:02<00:04, 42.70it/s]
Loading 0: 43%|████▎ | 125/291 [00:02<00:03, 42.24it/s]
Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 42.75it/s]
Loading 0: 46%|████▋ | 135/291 [00:03<00:03, 44.19it/s]
Loading 0: 48%|████▊ | 140/291 [00:03<00:04, 35.93it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:03, 44.39it/s]
Loading 0: 53%|█████▎ | 153/291 [00:03<00:03, 45.56it/s]
Loading 0: 54%|█████▍ | 158/291 [00:03<00:03, 36.91it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 44.64it/s]
Loading 0: 59%|█████▉ | 171/291 [00:04<00:02, 44.89it/s]
Loading 0: 60%|██████ | 176/291 [00:04<00:02, 45.51it/s]
Loading 0: 62%|██████▏ | 181/291 [00:04<00:02, 36.78it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 29.56it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 30.95it/s]
Loading 0: 67%|██████▋ | 195/291 [00:04<00:03, 31.04it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 36.63it/s]
Loading 0: 71%|███████ | 206/291 [00:05<00:02, 38.02it/s]
Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 39.87it/s]
Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 42.21it/s]
Loading 0: 76%|███████▌ | 221/291 [00:05<00:02, 34.48it/s]
Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 41.46it/s]
Loading 0: 80%|████████ | 233/291 [00:05<00:01, 41.74it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 41.62it/s]
Loading 0: 84%|████████▍ | 244/291 [00:06<00:01, 39.60it/s]
Loading 0: 86%|████████▌ | 249/291 [00:06<00:01, 39.87it/s]
Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 46.88it/s]
Loading 0: 90%|█████████ | 262/291 [00:06<00:00, 44.79it/s]
Loading 0: 92%|█████████▏| 267/291 [00:06<00:00, 43.64it/s]
Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 49.97it/s]
Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 45.80it/s]
Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 45.19it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 34.28it/s]
Job rirv938-llama-8b-scaleup-400k-v4-mkmlizer completed after 79.7s with status: succeeded
Stopping job with name rirv938-llama-8b-scaleup-400k-v4-mkmlizer
Pipeline stage MKMLizer completed in 80.96s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-scaleup-400k-v4
Waiting for inference service rirv938-llama-8b-scaleup-400k-v4 to be ready
Inference service rirv938-llama-8b-scaleup-200k-v2 ready after 91.01234245300293s
Pipeline stage MKMLDeployer completed in 92.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.157076597213745s
Inference service rirv938-llama-8b-scaleup-400k-v4 ready after 91.45428943634033s
Pipeline stage MKMLDeployer completed in 92.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.833306074142456s
Received healthy response to inference request in 4.256620645523071s
Received healthy response to inference request in 4.344254016876221s
Received healthy response to inference request in 2.9360430240631104s
Received healthy response to inference request in 4.768717050552368s
Received healthy response to inference request in 4.8915300369262695s
5 requests
0 failed requests
5th percentile: 2.853853464126587
10th percentile: 2.8744008541107178
20th percentile: 2.9154956340789795
30th percentile: 3.2176852226257324
40th percentile: 3.7809696197509766
50th percentile: 4.344254016876221
Received healthy response to inference request in 5.475637912750244s
60th percentile: 4.56316442489624
70th percentile: 4.782074832916259
80th percentile: 5.144639348983765
90th percentile: 5.650857973098755
95th percentile: 5.9039672851562495
99th percentile: 6.106454734802246
mean time: 4.23244194984436
Pipeline stage StressChecker completed in 26.18s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Received healthy response to inference request in 2.8939356803894043s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.68s
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 1.64s
Shutdown handler de-registered
rirv938-llama-8b-scaleup-200k_v2 status is now deployed due to DeploymentManager action
Received healthy response to inference request in 3.907116413116455s
5 requests
0 failed requests
5th percentile: 3.0965718269348144
10th percentile: 3.2992079734802244
20th percentile: 3.704480266571045
30th percentile: 3.9770172595977784
40th percentile: 4.116818952560425
50th percentile: 4.256620645523071
60th percentile: 4.46145920753479
70th percentile: 4.666297769546508
80th percentile: 4.910101222991943
90th percentile: 5.192869567871094
95th percentile: 5.334253740310669
99th percentile: 5.447361078262329
mean time: 4.260405540466309
Pipeline stage StressChecker completed in 24.69s
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 1.13s
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 1.15s
Shutdown handler de-registered
rirv938-llama-8b-scaleup-400k_v4 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...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Waiting for inference service rirv938-llama-8b-scaleup-400k-v4-profiler to be ready
Inference service rirv938-llama-8b-scaleup-400k-v4-profiler ready after 90.39847373962402s
Pipeline stage MKMLProfilerDeployer completed in 90.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deploltx2b:/code/chaiverse_profiler_1741725007 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deploltx2b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741725007 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1741725007/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-scaleup-400k-v4-profiler is running
Tearing down inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Service rirv938-llama-8b-scaleup-400k-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.29s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-scaleup-400k-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Waiting for inference service rirv938-llama-8b-scaleup-400k-v4-profiler to be ready
Inference service rirv938-llama-8b-scaleup-400k-v4-profiler ready after 80.32436990737915s
Pipeline stage MKMLProfilerDeployer completed in 80.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deplobcph9:/code/chaiverse_profiler_1741728624 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deplobcph9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741728624 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1741728624/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-scaleup-400k-v4-profiler is running
Tearing down inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Service rirv938-llama-8b-scaleup-400k-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.55s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-scaleup-400k-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Waiting for inference service rirv938-llama-8b-scaleup-400k-v4-profiler to be ready
Inference service rirv938-llama-8b-scaleup-400k-v4-profiler ready after 40.19347858428955s
Pipeline stage MKMLProfilerDeployer completed in 40.56s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deplohlp8v:/code/chaiverse_profiler_1741732110 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-scab2421f895bb21930ff92b816546e0e36-deplohlp8v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1741732110 && python profiles.py profile --best_of_n 1 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 1 --summary /code/chaiverse_profiler_1741732110/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-scaleup-400k-v4-profiler is running
Tearing down inference service rirv938-llama-8b-scaleup-400k-v4-profiler
Service rirv938-llama-8b-scaleup-400k-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.37s
Shutdown handler de-registered
rirv938-llama-8b-scaleup-400k_v4 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-scaleup-400k_v4 status is now torndown due to DeploymentManager action