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 zonemercy-vingt-deux-v0-1e5-v14-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v14-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: Downloaded to shared memory in 49.489s
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy_dm96gl, device:0
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: quantized model in 42.332s
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 91.821s
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/config.json
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/tokenizer.json
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v14/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v14-mkmlizer:
Loading 0: 0%| | 0/507 [00:00<?, ?it/s]
Loading 0: 1%| | 5/507 [00:00<00:17, 28.00it/s]
Loading 0: 2%|▏ | 12/507 [00:00<00:11, 43.63it/s]
Loading 0: 3%|▎ | 17/507 [00:00<00:12, 39.95it/s]
Loading 0: 4%|▍ | 22/507 [00:00<00:12, 39.96it/s]
Loading 0: 5%|▌ | 27/507 [00:00<00:11, 41.00it/s]
Loading 0: 6%|▋ | 32/507 [00:00<00:13, 35.66it/s]
Loading 0: 8%|▊ | 39/507 [00:00<00:10, 43.96it/s]
Loading 0: 9%|▊ | 44/507 [00:01<00:10, 44.27it/s]
Loading 0: 10%|▉ | 49/507 [00:01<00:12, 37.93it/s]
Loading 0: 11%|█ | 54/507 [00:01<00:15, 28.70it/s]
Loading 0: 11%|█▏ | 58/507 [00:01<00:15, 29.60it/s]
Loading 0: 12%|█▏ | 63/507 [00:01<00:13, 33.56it/s]
Loading 0: 13%|█▎ | 67/507 [00:01<00:13, 33.47it/s]
Loading 0: 14%|█▍ | 73/507 [00:02<00:11, 36.92it/s]
Loading 0: 16%|█▌ | 80/507 [00:02<00:10, 39.30it/s]
Loading 0: 17%|█▋ | 87/507 [00:02<00:09, 45.21it/s]
Loading 0: 18%|█▊ | 92/507 [00:02<00:09, 42.79it/s]
Loading 0: 19%|█▉ | 97/507 [00:02<00:09, 42.46it/s]
Loading 0: 20%|██ | 102/507 [00:02<00:09, 43.96it/s]
Loading 0: 21%|██ | 107/507 [00:02<00:10, 37.70it/s]
Loading 0: 22%|██▏ | 113/507 [00:03<00:12, 32.12it/s]
Loading 0: 23%|██▎ | 117/507 [00:03<00:12, 30.10it/s]
Loading 0: 24%|██▍ | 122/507 [00:03<00:12, 30.71it/s]
Loading 0: 25%|██▌ | 129/507 [00:03<00:09, 37.98it/s]
Loading 0: 26%|██▋ | 134/507 [00:03<00:09, 38.57it/s]
Loading 0: 27%|██▋ | 139/507 [00:03<00:09, 40.25it/s]
Loading 0: 28%|██▊ | 144/507 [00:03<00:08, 42.38it/s]
Loading 0: 29%|██▉ | 149/507 [00:03<00:09, 37.50it/s]
Loading 0: 31%|███ | 156/507 [00:04<00:08, 42.46it/s]
Loading 0: 32%|███▏ | 161/507 [00:04<00:08, 41.63it/s]
Loading 0: 33%|███▎ | 166/507 [00:04<00:07, 43.47it/s]
Loading 0: 34%|███▎ | 171/507 [00:04<00:12, 27.93it/s]
Loading 0: 35%|███▍ | 176/507 [00:04<00:10, 30.30it/s]
Loading 0: 36%|███▌ | 183/507 [00:04<00:08, 38.04it/s]
Loading 0: 37%|███▋ | 188/507 [00:05<00:08, 38.91it/s]
Loading 0: 38%|███▊ | 193/507 [00:05<00:07, 40.47it/s]
Loading 0: 39%|███▉ | 198/507 [00:05<00:07, 41.50it/s]
Loading 0: 40%|████ | 203/507 [00:05<00:08, 35.89it/s]
Loading 0: 41%|████▏ | 210/507 [00:05<00:06, 43.55it/s]
Loading 0: 42%|████▏ | 215/507 [00:05<00:06, 42.21it/s]
Loading 0: 43%|████▎ | 220/507 [00:05<00:07, 38.19it/s]
Loading 0: 44%|████▍ | 225/507 [00:06<00:09, 30.22it/s]
Loading 0: 45%|████▌ | 230/507 [00:06<00:08, 31.33it/s]
Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 37.83it/s]
Loading 0: 48%|████▊ | 242/507 [00:06<00:07, 34.96it/s]
Loading 0: 49%|████▊ | 247/507 [00:06<00:07, 36.36it/s]
Loading 0: 50%|████▉ | 251/507 [00:06<00:07, 36.19it/s]
Loading 0: 50%|█████ | 256/507 [00:06<00:06, 37.21it/s]
Loading 0: 51%|█████▏ | 260/507 [00:06<00:06, 37.39it/s]
Loading 0: 52%|█████▏ | 265/507 [00:07<00:06, 39.14it/s]
Loading 0: 53%|█████▎ | 269/507 [00:07<00:06, 39.26it/s]
Loading 0: 54%|█████▍ | 274/507 [00:07<00:05, 40.79it/s]
Loading 0: 55%|█████▌ | 279/507 [00:07<00:05, 40.93it/s]
Loading 0: 56%|█████▌ | 284/507 [00:07<00:07, 28.35it/s]
Loading 0: 57%|█████▋ | 288/507 [00:07<00:07, 27.70it/s]
Loading 0: 58%|█████▊ | 293/507 [00:08<00:07, 28.54it/s]
Loading 0: 59%|█████▉ | 299/507 [00:22<00:07, 28.54it/s]
Loading 0: 59%|█████▉ | 300/507 [00:22<02:50, 1.21it/s]
Loading 0: 60%|█████▉ | 302/507 [00:22<02:27, 1.39it/s]
Loading 0: 61%|██████ | 307/507 [00:22<01:38, 2.03it/s]
Loading 0: 61%|██████ | 310/507 [00:22<01:18, 2.52it/s]
Loading 0: 62%|██████▏ | 315/507 [00:23<00:51, 3.73it/s]
Loading 0: 63%|██████▎ | 319/507 [00:23<00:37, 5.01it/s]
Loading 0: 64%|██████▍ | 325/507 [00:23<00:24, 7.51it/s]
Loading 0: 65%|██████▍ | 329/507 [00:23<00:19, 9.25it/s]
Loading 0: 66%|██████▌ | 335/507 [00:23<00:13, 13.20it/s]
Loading 0: 67%|██████▋ | 340/507 [00:23<00:11, 14.86it/s]
Loading 0: 68%|██████▊ | 344/507 [00:23<00:09, 17.24it/s]
Loading 0: 69%|██████▊ | 348/507 [00:24<00:08, 19.36it/s]
Loading 0: 70%|██████▉ | 354/507 [00:24<00:06, 25.47it/s]
Loading 0: 71%|███████ | 358/507 [00:24<00:05, 27.61it/s]
Loading 0: 72%|███████▏ | 364/507 [00:24<00:04, 32.50it/s]
Loading 0: 73%|███████▎ | 369/507 [00:24<00:03, 34.88it/s]
Loading 0: 74%|███████▍ | 374/507 [00:24<00:04, 31.61it/s]
Loading 0: 75%|███████▌ | 382/507 [00:24<00:03, 39.80it/s]
Loading 0: 77%|███████▋ | 388/507 [00:24<00:02, 40.90it/s]
Loading 0: 78%|███████▊ | 393/507 [00:25<00:02, 39.93it/s]
Loading 0: 79%|███████▊ | 398/507 [00:25<00:03, 32.51it/s]
Loading 0: 79%|███████▉ | 402/507 [00:25<00:03, 30.77it/s]
Loading 0: 80%|████████ | 408/507 [00:25<00:02, 35.76it/s]
Loading 0: 81%|████████▏ | 412/507 [00:25<00:02, 34.48it/s]
Loading 0: 82%|████████▏ | 417/507 [00:25<00:02, 37.44it/s]
Loading 0: 83%|████████▎ | 421/507 [00:25<00:02, 36.00it/s]
Loading 0: 84%|████████▍ | 427/507 [00:26<00:02, 39.37it/s]
Loading 0: 85%|████████▌ | 432/507 [00:26<00:01, 41.70it/s]
Loading 0: 86%|████████▌ | 437/507 [00:26<00:01, 36.99it/s]
Loading 0: 88%|████████▊ | 445/507 [00:26<00:01, 44.71it/s]
Loading 0: 89%|████████▉ | 451/507 [00:26<00:01, 43.86it/s]
Loading 0: 90%|████████▉ | 456/507 [00:28<00:06, 7.52it/s]
Loading 0: 91%|█████████ | 460/507 [00:28<00:05, 9.02it/s]
Loading 0: 92%|█████████▏| 465/507 [00:29<00:03, 11.35it/s]
Loading 0: 93%|█████████▎| 472/507 [00:29<00:02, 16.24it/s]
Loading 0: 94%|█████████▍| 476/507 [00:29<00:01, 18.42it/s]
Loading 0: 95%|█████████▍| 481/507 [00:29<00:01, 22.33it/s]
Loading 0: 96%|█████████▌| 486/507 [00:29<00:00, 25.86it/s]
Loading 0: 97%|█████████▋| 491/507 [00:29<00:00, 29.24it/s]
Loading 0: 98%|█████████▊| 496/507 [00:29<00:00, 33.30it/s]
Loading 0: 99%|█████████▉| 501/507 [00:30<00:00, 29.76it/s]
Job zonemercy-vingt-deux-v0-1e5-v14-mkmlizer completed after 116.46s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v14-mkmlizer
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLizer completed in 119.47s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v14
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v14 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v14 ready after 191.05003094673157s
Pipeline stage MKMLDeployer completed in 191.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6849734783172607s
Received healthy response to inference request in 2.907914161682129s
Received healthy response to inference request in 3.2951180934906006s
Received healthy response to inference request in 3.5987813472747803s
Received healthy response to inference request in 3.6828083992004395s
5 requests
0 failed requests
5th percentile: 2.985354948043823
10th percentile: 3.0627957344055177
20th percentile: 3.2176773071289064
30th percentile: 3.3558507442474363
40th percentile: 3.4773160457611083
50th percentile: 3.5987813472747803
60th percentile: 3.632392168045044
70th percentile: 3.6660029888153076
80th percentile: 3.6832414150238035
90th percentile: 3.684107446670532
95th percentile: 3.6845404624938967
99th percentile: 3.684886875152588
mean time: 3.433919095993042
Pipeline stage StressChecker completed in 18.85s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 6.13s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v14 status is now deployed due to DeploymentManager action
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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v14-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v14-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v14-profiler ready after 190.4361231327057s
Pipeline stage MKMLProfilerDeployer completed in 190.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxaff99c9476f84993e510c116774c5220-deplo7h5cg:/code/chaiverse_profiler_1727085916 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxaff99c9476f84993e510c116774c5220-deplo7h5cg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727085916 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727085916/summary.json'
kubectl exec -it zonemercy-vingt-deuxaff99c9476f84993e510c116774c5220-deplo7h5cg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727085916/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1562.49s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v14-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v14-profiler
Service zonemercy-vingt-deux-v0-1e5-v14-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.97s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v14 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of zonemercy-vingt-deux-v0-1e5_v14
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
admin requested tearing down of zonemercy-vingt-deux-v0-_4921_v5
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
Checking if service zonemercy-vingt-deux-v0-1e5-v14 is running
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service zonemercy-vingt-deux-v0-4921-v5 is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v14
Service zonemercy-vingt-deux-v0-1e5-v14 has been torndown
Pipeline stage MKMLDeleter completed in 1.90s
Tearing down inference service zonemercy-vingt-deux-v0-4921-v5
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Service zonemercy-vingt-deux-v0-4921-v5 has been torndown
Cleaning model data from S3
Pipeline stage MKMLDeleter completed in 1.93s
Cleaning model data from model cache
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Deleting key zonemercy-vingt-deux-v0-1e5-v14/config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key zonemercy-vingt-deux-v0-1e5-v14/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-4921-v5/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-4921-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v14/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-4921-v5/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v14/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v14/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-1e5-v14/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-4921-v5/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 2.72s
Deleting key zonemercy-vingt-deux-v0-4921-v5/tokenizer.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Deleting key zonemercy-vingt-deux-v0-4921-v5/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v0-4921-v5/tokenizer_config.json from bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5_v14 status is now torndown due to DeploymentManager action