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-llama8b-retune7-81771-v1-mkmlizer
Waiting for job on chaiml-llama8b-retune7-81771-v1-mkmlizer to finish
chaiml-llama8b-retune7-81771-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║                                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║                                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║                                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║                                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ║                                                                     ║
chaiml-llama8b-retune7-81771-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-retune7-81771-v1-mkmlizer: Downloaded to shared memory in 36.645s
chaiml-llama8b-retune7-81771-v1-mkmlizer: Checking if ChaiML/llama8b-retune7-rm-pointwise-900kdata-wffaux-w1-difflin already exists in ChaiML
chaiml-llama8b-retune7-81771-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp0tub5e8q, device:0
chaiml-llama8b-retune7-81771-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-retune7-81771-v1-mkmlizer: quantized model in 19.406s
chaiml-llama8b-retune7-81771-v1-mkmlizer: Processed model ChaiML/llama8b-retune7-rm-pointwise-900kdata-wffaux-w1-difflin in 56.052s
chaiml-llama8b-retune7-81771-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-retune7-81771-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8b-retune7-81771-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1
chaiml-llama8b-retune7-81771-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1/config.json
chaiml-llama8b-retune7-81771-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1/special_tokens_map.json
chaiml-llama8b-retune7-81771-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1/tokenizer_config.json
chaiml-llama8b-retune7-81771-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1/tokenizer.json
chaiml-llama8b-retune7-81771-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama8b-retune7-81771-v1/flywheel_model.0.safetensors
chaiml-llama8b-retune7-81771-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.89it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 56.68it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:05, 53.48it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:04, 53.75it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 46.57it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 55.05it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:04, 51.01it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:04, 51.86it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 46.97it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 54.01it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 50.61it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 51.64it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 35.36it/s]
Loading 0:  31%|███       | 90/291 [00:01<00:05, 38.19it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 35.67it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 44.59it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 42.12it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 41.78it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 47.92it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 46.46it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 45.69it/s]
Loading 0:  47%|████▋     | 138/291 [00:02<00:03, 49.00it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:02, 49.81it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 43.36it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 48.77it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 43.27it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 41.09it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 41.40it/s]
Loading 0:  61%|██████    | 178/291 [00:03<00:02, 43.30it/s]
Loading 0:  63%|██████▎   | 183/291 [00:04<00:02, 40.28it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:03, 28.94it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:03, 30.51it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 31.96it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 37.42it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:02, 40.09it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:02, 34.98it/s]
Loading 0:  76%|███████▌  | 220/291 [00:05<00:01, 43.69it/s]
Loading 0:  77%|███████▋  | 225/291 [00:05<00:01, 44.43it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 37.08it/s]
Loading 0:  81%|████████▏ | 237/291 [00:05<00:01, 44.34it/s]
Loading 0:  83%|████████▎ | 242/291 [00:05<00:01, 43.13it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:01, 43.72it/s]
Loading 0:  87%|████████▋ | 252/291 [00:05<00:00, 45.32it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 38.56it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 47.77it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 46.62it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 46.06it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 43.03it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 33.90it/s]
                                                            
Job chaiml-llama8b-retune7-81771-v1-mkmlizer completed after 84.49s with status: succeeded
Stopping job with name chaiml-llama8b-retune7-81771-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.99s
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-llama8b-retune7-81771-v1
Waiting for inference service chaiml-llama8b-retune7-81771-v1 to be ready
Inference service chaiml-llama8b-retune7-81771-v1 ready after 151.24996376037598s
Pipeline stage MKMLDeployer completed in 151.79s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.569938898086548s
Received healthy response to inference request in 3.707984685897827s
Received healthy response to inference request in 4.2152063846588135s
Received healthy response to inference request in 3.6789603233337402s
Received healthy response to inference request in 4.924762487411499s
5 requests
0 failed requests
5th percentile: 3.5917431831359865
10th percentile: 3.6135474681854247
20th percentile: 3.6571560382843016
30th percentile: 3.6847651958465577
40th percentile: 3.696374940872192
50th percentile: 3.707984685897827
60th percentile: 3.910873365402222
70th percentile: 4.113762044906617
80th percentile: 4.357117605209351
90th percentile: 4.6409400463104244
95th percentile: 4.782851266860962
99th percentile: 4.896380243301391
mean time: 4.0193705558776855
Pipeline stage StressChecker completed in 22.09s
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 0.66s
Shutdown handler de-registered
chaiml-llama8b-retune7-_81771_v1 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-retune7-81771-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-81771-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-81771-v1-profiler ready after 141.2528898715973s
Pipeline stage MKMLProfilerDeployer completed in 142.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr:/code/chaiverse_profiler_1750827785 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750827785 && 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_1750827785/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr:/code/chaiverse_profiler_1750828202 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750828202 && 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_1750828202/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr:/code/chaiverse_profiler_1750828616 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplow6jhr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750828616 && 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_1750828616/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n  0%|          | 0/200 [00:00<?, ?it/s]\n  0%|          | 1/200 [00:00<00:49,  4.02it/s]\n  1%|          | 2/200 [00:03<06:50,  2.07s/it]\n  2%|▏         | 3/200 [00:03<04:02,  1.23s/it]\n  2%|▏         | 4/200 [00:04<02:45,  1.19it/s]\n  2%|▎         | 5/200 [00:04<02:01,  1.60it/s]\n  3%|▎         | 6/200 [00:07<05:04,  1.57s/it]\n  4%|▎         | 7/200 [00:07<03:38,  1.13s/it]\n  4%|▍         | 8/200 [00:08<02:45,  1.16it/s]\n  4%|▍         | 9/200 [00:11<05:21,  1.68s/it]\n  5%|▌         | 10/200 [00:15<06:58,  2.20s/it]\n  6%|▌         | 11/200 [00:15<04:55,  1.56s/it]\n  6%|▌         | 12/200 [00:18<06:46,  2.16s/it]\n  6%|▋         | 13/200 [00:18<04:48,  1.54s/it]\n  7%|▋         | 14/200 [00:22<06:43,  2.17s/it]\n  8%|▊         | 15/200 [00:22<04:46,  1.55s/it]\n  8%|▊         | 16/200 [00:22<03:33,  1.16s/it]\n  8%|▊         | 17/200 [00:26<05:39,  1.85s/it]\n  9%|▉         | 18/200 [00:26<04:07,  1.36s/it]\n 10%|▉         | 19/200 [00:30<06:02,  2.00s/it]\n 10%|█         | 20/200 [00:30<04:19,  1.44s/it]\n 10%|█         | 21/200 [00:33<06:03,  2.03s/it]\n 11%|█         | 22/200 [00:33<04:25,  1.49s/it]\n 12%|█▏        | 23/200 [00:37<06:14,  2.12s/it]\n 12%|█▏        | 24/200 [00:40<07:24,  2.53s/it]\n 12%|█▎        | 25/200 [00:40<05:16,  1.81s/it]\n 13%|█▎        | 26/200 [00:44<06:41,  2.31s/it]\n 14%|█▎        | 27/200 [00:48<07:51,  2.72s/it]\n 14%|█▍        | 28/200 [00:48<05:34,  1.94s/it]\n 14%|█▍        | 29/200 [00:51<06:46,  2.38s/it]\n 15%|█▌        | 30/200 [00:55<07:44,  2.73s/it]\n 16%|█▌        | 31/200 [00:58<08:16,  2.94s/it]\n 16%|█▌        | 32/200 [01:02<08:41,  3.10s/it]\n 16%|█▋        | 33/200 [01:02<06:08,  2.21s/it]\n 17%|█▋        | 34/200 [01:05<07:10,  2.59s/it]\n 18%|█▊        | 35/200 [01:05<05:10,  1.88s/it]\n 18%|█▊        | 36/200 [01:09<06:31,  2.39s/it]\n 18%|█▊        | 37/200 [01:13<07:23,  2.72s/it]\n 19%|█▉        | 38/200 [01:16<07:57,  2.94s/it]\n 20%|█▉        | 39/200 [01:20<08:21,  3.12s/it]\n 20%|██        | 40/200 [01:23<08:30,  3.19s/it]\n 20%|██        | 41/200 [01:23<06:01,  2.27s/it]\n 21%|██        | 42/200 [01:23<04:23,  1.67s/it]\n 22%|██▏       | 43/200 [01:23<03:14,  1.24s/it]\n 22%|██▏       | 44/200 [01:27<04:56,  1.90s/it]\n 22%|██▎       | 45/200 [01:30<06:05,  2.36s/it]\n 23%|██▎       | 46/200 [01:31<04:24,  1.72s/it]\n 24%|██▎       | 47/200 [01:31<03:15,  1.28s/it]\n 24%|██▍       | 48/200 [01:34<04:52,  1.92s/it]\n 24%|██▍       | 49/200 [01:35<03:35,  1.42s/it]\n 25%|██▌       | 50/200 [01:38<05:04,  2.03s/it]\n 26%|██▌       | 51/200 [01:38<03:42,  1.49s/it]\n 26%|██▌       | 52/200 [01:38<02:45,  1.12s/it]\n 26%|██▋       | 53/200 [01:39<02:06,  1.17it/s]\n 27%|██▋       | 54/200 [01:39<01:38,  1.49it/s]\n 28%|██▊       | 55/200 [01:42<03:36,  1.49s/it]\n 28%|██▊       | 56/200 [01:43<02:41,  1.12s/it]\n 28%|██▊       | 57/200 [01:46<04:19,  1.82s/it]\n 29%|██▉       | 58/200 [01:49<05:25,  2.29s/it]\n 30%|██▉       | 59/200 [01:53<06:10,  2.63s/it]\n 30%|███       | 60/200 [01:56<06:35,  2.83s/it]\n 30%|███       | 61/200 [01:56<04:45,  2.05s/it]\n 31%|███       | 62/200 [01:57<03:29,  1.52s/it]\n 32%|███▏      | 63/200 [02:00<04:47,  2.10s/it]\n 32%|███▏      | 64/200 [02:04<05:46,  2.55s/it]\n 32%|███▎      | 65/200 [02:07<06:21,  2.83s/it]\n 33%|███▎      | 66/200 [02:07<04:30,  2.02s/it]\n 34%|███▎      | 67/200 [02:08<03:18,  1.49s/it]\n 34%|███▍      | 68/200 [02:11<04:33,  2.07s/it]\n 34%|███▍      | 69/200 [02:15<05:28,  2.51s/it]\n 35%|███▌      | 70/200 [02:18<06:00,  2.77s/it]\n 36%|███▌      | 71/200 [02:21<06:21,  2.96s/it]\n 36%|███▌      | 72/200 [02:25<06:39,  3.12s/it]\n 36%|███▋      | 73/200 [02:25<04:41,  2.22s/it]\n 37%|███▋      | 74/200 [02:28<05:30,  2.62s/it]\n 38%|███▊      | 75/200 [02:32<05:57,  2.86s/it]\n 38%|███▊      | 76/200 [02:32<04:12,  2.04s/it]\n 38%|███▊      | 77/200 [02:36<05:03,  2.47s/it]\n 39%|███▉      | 78/200 [02:39<05:32,  2.73s/it]\n 40%|███▉      | 79/200 [02:39<03:59,  1.98s/it]\n 40%|████      | 80/200 [02:39<02:55,  1.46s/it]\n 40%|████      | 81/200 [02:43<04:03,  2.04s/it]\n 41%|████      | 82/200 [02:46<04:54,  2.50s/it]\n 42%|████▏     | 83/200 [02:46<03:28,  1.79s/it]\n 42%|████▏     | 84/200 [02:50<04:24,  2.28s/it]\n 42%|████▎     | 85/200 [02:53<05:04,  2.65s/it]\n 43%|████▎     | 86/200 [02:53<03:35,  1.89s/it]\n 44%|████▎     | 87/200 [02:57<04:24,  2.34s/it]\n 44%|████▍     | 88/200 [03:00<05:01,  2.69s/it]\n 44%|████▍     | 89/200 [03:04<05:22,  2.91s/it]\n 45%|████▌     | 90/200 [03:07<05:35,  3.05s/it]\n 46%|████▌     | 91/200 [03:11<05:44,  3.16s/it]\n 46%|████▌     | 92/200 [03:11<04:02,  2.25s/it]\n 46%|████▋     | 93/200 [03:11<02:56,  1.65s/it]\n 47%|████▋     | 94/200 [03:14<03:50,  2.17s/it]\n 48%|████▊     | 95/200 [03:15<02:46,  1.59s/it]\n 48%|████▊     | 96/200 [03:15<02:03,  1.18s/it]\n 48%|████▊     | 97/200 [03:15<01:32,  1.11it/s]\n 49%|████▉     | 98/200 [03:18<02:47,  1.64s/it]\n 50%|████▉     | 99/200 [03:19<02:03,  1.22s/it]\n 50%|█████     | 100/200 [03:22<03:09,  1.89s/it]\n 50%|█████     | 101/200 [03:22<02:18,  1.39s/it]\n 51%|█████     | 102/200 [03:26<03:15,  2.00s/it]\n 52%|█████▏    | 103/200 [03:29<03:54,  2.41s/it]\n 52%|█████▏    | 104/200 [03:29<02:49,  1.76s/it]\n 52%|█████▎    | 105/200 [03:33<03:35,  2.26s/it]\n 53%|█████▎    | 106/200 [03:36<04:04,  2.60s/it]\n 54%|█████▎    | 107/200 [03:36<02:55,  1.89s/it]\n 54%|█████▍    | 108/200 [03:40<03:35,  2.34s/it]\n 55%|█████▍    | 109/200 [03:43<04:02,  2.67s/it]\n 55%|█████▌    | 110/200 [03:44<02:54,  1.94s/it]\n 56%|█████▌    | 111/200 [03:44<02:07,  1.43s/it]\n 56%|█████▌    | 112/200 [03:47<03:00,  2.05s/it]\n 56%|█████▋    | 113/200 [03:47<02:10,  1.50s/it]\n 57%|█████▋    | 114/200 [03:51<03:01,  2.11s/it]\n 57%|█████▊    | 115/200 [03:54<03:32,  2.50s/it]\n 58%|█████▊    | 116/200 [03:55<02:33,  1.82s/it]\n 58%|█████▊    | 117/200 [03:55<01:52,  1.35s/it]\n 59%|█████▉    | 118/200 [03:58<02:42,  1.99s/it]\n 60%|█████▉    | 119/200 [04:02<03:17,  2.44s/it]\n 60%|██████    | 120/200 [04:02<02:22,  1.79s/it]\n 60%|██████    | 121/200 [04:02<01:41,  1.29s/it]\n 61%|██████    | 122/200 [04:03<01:16,  1.02it/s]\n 62%|██████▏   | 123/200 [04:06<02:16,  1.77s/it]\n 62%|██████▏   | 124/200 [04:10<02:52,  2.28s/it]\n 62%|██████▎   | 125/200 [04:13<03:16,  2.61s/it]\n 63%|██████▎   | 126/200 [04:16<03:31,  2.85s/it]\n 64%|██████▎   | 127/200 [04:20<03:41,  3.04s/it]\n 64%|██████▍   | 128/200 [04:20<02:35,  2.16s/it]\n 64%|██████▍   | 129/200 [04:23<03:01,  2.56s/it]\n 65%|██████▌   | 130/200 [04:24<02:07,  1.83s/it]\n 66%|██████▌   | 131/200 [04:24<01:33,  1.35s/it]\n 66%|██████▌   | 132/200 [04:24<01:08,  1.01s/it]\n 66%|██████▋   | 133/200 [04:27<01:56,  1.74s/it]\n 67%|██████▋   | 134/200 [04:28<01:24,  1.29s/it]\n 68%|██████▊   | 135/200 [04:31<02:04,  1.92s/it]\n 68%|██████▊   | 136/200 [04:34<02:30,  2.35s/it]\n 68%|██████▊   | 137/200 [04:35<01:48,  1.72s/it]\n 69%|██████▉   | 138/200 [04:35<01:19,  1.28s/it]\n 70%|██████▉   | 139/200 [04:38<01:57,  1.92s/it]\n 70%|███████   | 140/200 [04:42<02:24,  2.40s/it]\n 70%|███████   | 141/200 [04:45<02:39,  2.70s/it]\n 71%|███████   | 142/200 [04:49<02:49,  2.91s/it]\n 72%|███████▏  | 143/200 [04:52<02:55,  3.08s/it]\n 72%|███████▏  | 144/200 [04:52<02:02,  2.19s/it]\n 72%|███████▎  | 145/200 [04:53<01:28,  1.60s/it]\n 73%|███████▎  | 146/200 [04:53<01:04,  1.19s/it]\n 74%|███████▎  | 147/200 [04:53<00:48,  1.10it/s]\n 74%|███████▍  | 148/200 [04:56<01:25,  1.65s/it]\n 74%|███████▍  | 149/200 [05:00<01:51,  2.19s/it]\n 75%|███████▌  | 150/200 [05:00<01:20,  1.60s/it]\n 76%|███████▌  | 151/200 [05:04<01:45,  2.15s/it]\n 76%|███████▌  | 152/200 [05:07<02:01,  2.53s/it]\n 76%|███████▋  | 153/200 [05:07<01:27,  1.85s/it]\n 77%|███████▋  | 154/200 [05:11<01:48,  2.36s/it]\n 78%|███████▊  | 155/200 [05:14<02:02,  2.72s/it]\n 78%|███████▊  | 156/200 [05:18<02:08,  2.92s/it]\n 78%|███████▊  | 157/200 [05:18<01:31,  2.12s/it]\n 79%|███████▉  | 158/200 [05:21<01:45,  2.52s/it]\n 80%|███████▉  | 159/200 [05:25<01:54,  2.80s/it]\n 80%|████████  | 160/200 [05:25<01:21,  2.04s/it]\n 80%|████████  | 161/200 [05:28<01:35,  2.44s/it]\n 81%|████████  | 162/200 [05:29<01:07,  1.78s/it]\n 82%|████████▏ | 163/200 [05:29<00:48,  1.32s/it]\n 82%|████████▏ | 164/200 [05:29<00:35,  1.00it/s]\n 82%|████████▎ | 165/200 [05:33<01:01,  1.76s/it]\n 83%|████████▎ | 166/200 [05:33<00:42,  1.26s/it]\n 84%|████████▎ | 167/200 [05:36<01:02,  1.91s/it]\n 84%|████████▍ | 168/200 [05:37<00:44,  1.40s/it]\n 84%|████████▍ | 169/200 [05:40<01:03,  2.05s/it]\n 85%|████████▌ | 170/200 [05:44<01:14,  2.47s/it]\n 86%|████████▌ | 171/200 [05:47<01:19,  2.75s/it]\n 86%|████████▌ | 172/200 [05:47<00:55,  1.97s/it]\n 86%|████████▋ | 173/200 [05:51<01:06,  2.45s/it]\n 87%|████████▋ | 174/200 [05:54<01:11,  2.74s/it]\n 88%|████████▊ | 175/200 [05:54<00:48,  1.95s/it]\n 88%|████████▊ | 176/200 [05:58<00:57,  2.40s/it]\n 88%|████████▊ | 177/200 [06:01<01:02,  2.74s/it]\n 89%|████████▉ | 178/200 [06:05<01:04,  2.95s/it]\n 90%|████████▉ | 179/200 [06:05<00:44,  2.10s/it]\n 90%|█████████ | 180/200 [06:05<00:30,  1.55s/it]\n 90%|█████████ | 181/200 [06:05<00:22,  1.16s/it]\n 91%|█████████ | 182/200 [06:09<00:33,  1.84s/it]\n 92%|█████████▏| 183/200 [06:09<00:23,  1.36s/it]\n 92%|█████████▏| 184/200 [06:09<00:16,  1.03s/it]\n 92%|█████████▎| 185/200 [06:13<00:26,  1.75s/it]\n 93%|█████████▎| 186/200 [06:13<00:18,  1.30s/it]\n 94%|█████████▎| 187/200 [06:16<00:25,  1.96s/it]\n 94%|█████████▍| 188/200 [06:17<00:17,  1.44s/it]\n 94%|█████████▍| 189/200 [06:20<00:22,  2.04s/it]\n 95%|█████████▌| 190/200 [06:20<00:14,  1.50s/it]\n 96%|█████████▌| 191/200 [06:24<00:18,  2.07s/it]\n 96%|█████████▌| 192/200 [06:24<00:12,  1.53s/it]\n 96%|█████████▋| 193/200 [06:24<00:08,  1.15s/it]\n 97%|█████████▋| 194/200 [06:28<00:11,  1.86s/it]\n 98%|█████████▊| 195/200 [06:31<00:11,  2.31s/it]\n 98%|█████████▊| 196/200 [06:34<00:10,  2.64s/it]\n 98%|█████████▊| 197/200 [06:38<00:08,  2.89s/it]\n 99%|█████████▉| 198/200 [06:38<00:04,  2.06s/it]\n100%|█████████▉| 199/200 [06:38<00:01,  1.52s/it]\n100%|██████████| 200/200 [06:39<00:00,  1.13s/it]\n100%|██████████| 200/200 [06:39<00:00,  2.00s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1750828616/profiles.py", line 621, in <module>\n    cli()\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n    return self.main(*args, **kwargs)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n    rv = self.invoke(ctx)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n    return _process_result(sub_ctx.command.invoke(sub_ctx))\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n    return ctx.invoke(self.callback, **ctx.params)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n    return __callback(*args, **kwargs)\n  File "/code/chaiverse_profiler_1750828616/profiles.py", line 112, in profile_batches\n    profiles = run_batch_profile_with_auto_batch(target, batches, settings, auto_batch, output)\n  File "/code/chaiverse_profiler_1750828616/profiles.py", line 163, in run_batch_profile_with_auto_batch\n    profiles = run_batch_profile(target, batches, settings, output)\n  File "/code/chaiverse_profiler_1750828616/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 399.0182521343231\nerrors 90\nmean length: 1.65\n\nthroughput (request / second): 0.5012302042079849\nthroughput (character / second): 0.8270298369431751\naverage request duration (s) 1.9949742460250854\n50%ile request duration (s) 3.3818295001983643\n75%ile request duration (s) 3.444059729576111\n90%ile request duration (s) 3.511124801635742\n95%ile request duration (s) 3.55610728263855\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-81771-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-81771-v1-profiler
Service chaiml-llama8b-retune7-81771-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.26s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-81771-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.38s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-retune7-81771-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-81771-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-81771-v1-profiler ready after 141.24971890449524s
Pipeline stage MKMLProfilerDeployer completed in 141.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9:/code/chaiverse_profiler_1750829247 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750829247 && 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_1750829247/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9:/code/chaiverse_profiler_1750829639 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750829639 && 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_1750829639/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9:/code/chaiverse_profiler_1750830070 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplokwmh9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750830070 && 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_1750830070/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n  0%|          | 0/200 [00:00<?, ?it/s]\n  0%|          | 1/200 [00:00<00:48,  4.07it/s]\n  1%|          | 2/200 [00:03<07:02,  2.13s/it]\n  2%|▏         | 3/200 [00:07<08:52,  2.70s/it]\n  2%|▏         | 4/200 [00:07<05:30,  1.69s/it]\n  2%|▎         | 5/200 [00:07<03:48,  1.17s/it]\n  3%|▎         | 6/200 [00:07<02:48,  1.15it/s]\n  4%|▎         | 7/200 [00:11<05:31,  1.72s/it]\n  4%|▍         | 8/200 [00:11<04:00,  1.25s/it]\n  4%|▍         | 9/200 [00:14<06:10,  1.94s/it]\n  5%|▌         | 10/200 [00:15<04:30,  1.42s/it]\n  6%|▌         | 11/200 [00:15<03:22,  1.07s/it]\n  6%|▌         | 12/200 [00:18<05:41,  1.82s/it]\n  6%|▋         | 13/200 [00:22<07:09,  2.30s/it]\n  7%|▋         | 14/200 [00:25<08:10,  2.64s/it]\n  8%|▊         | 15/200 [00:26<05:56,  1.93s/it]\n  8%|▊         | 16/200 [00:29<07:15,  2.37s/it]\n  8%|▊         | 17/200 [00:32<08:08,  2.67s/it]\n  9%|▉         | 18/200 [00:36<08:45,  2.89s/it]\n 10%|▉         | 19/200 [00:39<09:16,  3.07s/it]\n 10%|█         | 20/200 [00:40<06:40,  2.23s/it]\n 10%|█         | 21/200 [00:40<04:53,  1.64s/it]\n 11%|█         | 22/200 [00:40<03:32,  1.19s/it]\n 12%|█▏        | 23/200 [00:40<02:43,  1.08it/s]\n 12%|█▏        | 24/200 [00:44<04:53,  1.67s/it]\n 12%|█▎        | 25/200 [00:47<06:30,  2.23s/it]\n 13%|█▎        | 26/200 [00:47<04:37,  1.60s/it]\n 14%|█▎        | 27/200 [00:48<03:27,  1.20s/it]\n 14%|█▍        | 28/200 [00:48<02:38,  1.08it/s]\n 14%|█▍        | 29/200 [00:48<02:04,  1.37it/s]\n 15%|█▌        | 30/200 [00:52<04:20,  1.53s/it]\n 16%|█▌        | 31/200 [00:55<05:51,  2.08s/it]\n 16%|█▌        | 32/200 [00:58<06:54,  2.47s/it]\n 16%|█▋        | 33/200 [00:58<05:01,  1.80s/it]\n 17%|█▋        | 34/200 [00:59<03:42,  1.34s/it]\n 18%|█▊        | 35/200 [00:59<02:48,  1.02s/it]\n 18%|█▊        | 36/200 [01:02<04:44,  1.74s/it]\n 18%|█▊        | 37/200 [01:03<03:30,  1.29s/it]\n 19%|█▉        | 38/200 [01:06<05:11,  1.92s/it]\n 20%|█▉        | 39/200 [01:10<06:27,  2.40s/it]\n 20%|██        | 40/200 [01:13<07:12,  2.70s/it]\n 20%|██        | 41/200 [01:13<05:13,  1.97s/it]\n 21%|██        | 42/200 [01:17<06:17,  2.39s/it]\n 22%|██▏       | 43/200 [01:20<07:02,  2.69s/it]\n 22%|██▏       | 44/200 [01:23<07:33,  2.91s/it]\n 22%|██▎       | 45/200 [01:27<07:50,  3.04s/it]\n 23%|██▎       | 46/200 [01:30<08:03,  3.14s/it]\n 24%|██▎       | 47/200 [01:34<08:11,  3.21s/it]\n 24%|██▍       | 48/200 [01:34<05:47,  2.29s/it]\n 24%|██▍       | 49/200 [01:37<06:44,  2.68s/it]\n 25%|██▌       | 50/200 [01:37<04:46,  1.91s/it]\n 26%|██▌       | 51/200 [01:41<05:56,  2.39s/it]\n 26%|██▌       | 52/200 [01:44<06:37,  2.69s/it]\n 26%|██▋       | 53/200 [01:44<04:41,  1.92s/it]\n 27%|██▋       | 54/200 [01:45<03:27,  1.42s/it]\n 28%|██▊       | 55/200 [01:48<04:51,  2.01s/it]\n 28%|██▊       | 56/200 [01:51<05:49,  2.42s/it]\n 28%|██▊       | 57/200 [01:55<06:39,  2.80s/it]\n 29%|██▉       | 58/200 [01:55<04:43,  2.00s/it]\n 30%|██▉       | 59/200 [01:59<05:42,  2.43s/it]\n 30%|███       | 60/200 [01:59<04:10,  1.79s/it]\n 30%|███       | 61/200 [02:02<05:15,  2.27s/it]\n 31%|███       | 62/200 [02:03<03:51,  1.68s/it]\n 32%|███▏      | 63/200 [02:06<05:03,  2.21s/it]\n 32%|███▏      | 64/200 [02:10<05:57,  2.63s/it]\n 32%|███▎      | 65/200 [02:13<06:18,  2.81s/it]\n 33%|███▎      | 66/200 [02:16<06:44,  3.02s/it]\n 34%|███▎      | 67/200 [02:17<04:45,  2.15s/it]\n 34%|███▍      | 68/200 [02:20<05:33,  2.53s/it]\n 34%|███▍      | 69/200 [02:20<04:01,  1.85s/it]\n 35%|███▌      | 70/200 [02:21<02:58,  1.37s/it]\n 36%|███▌      | 71/200 [02:24<04:16,  1.98s/it]\n 36%|███▌      | 72/200 [02:27<05:10,  2.43s/it]\n 36%|███▋      | 73/200 [02:28<03:46,  1.79s/it]\n 37%|███▋      | 74/200 [02:31<04:46,  2.28s/it]\n 38%|███▊      | 75/200 [02:34<05:26,  2.61s/it]\n 38%|███▊      | 76/200 [02:38<05:55,  2.87s/it]\n 38%|███▊      | 77/200 [02:42<06:20,  3.09s/it]\n 39%|███▉      | 78/200 [02:45<06:27,  3.17s/it]\n 40%|███▉      | 79/200 [02:48<06:33,  3.25s/it]\n 40%|████      | 80/200 [02:48<04:37,  2.31s/it]\n 40%|████      | 81/200 [02:49<03:22,  1.70s/it]\n 41%|████      | 82/200 [02:49<02:31,  1.28s/it]\n 42%|████▏     | 83/200 [02:49<01:54,  1.02it/s]\n 42%|████▏     | 84/200 [02:53<03:19,  1.72s/it]\n 42%|████▎     | 85/200 [02:56<04:16,  2.23s/it]\n 43%|████▎     | 86/200 [03:00<04:56,  2.60s/it]\n 44%|████▎     | 87/200 [03:03<05:23,  2.86s/it]\n 44%|████▍     | 88/200 [03:07<05:39,  3.03s/it]\n 44%|████▍     | 89/200 [03:10<05:53,  3.19s/it]\n 45%|████▌     | 90/200 [03:10<04:09,  2.27s/it]\n 46%|████▌     | 91/200 [03:14<04:51,  2.68s/it]\n 46%|████▌     | 92/200 [03:14<03:26,  1.91s/it]\n 46%|████▋     | 93/200 [03:18<04:16,  2.40s/it]\n 47%|████▋     | 94/200 [03:18<03:01,  1.71s/it]\n 48%|████▊     | 95/200 [03:21<03:56,  2.25s/it]\n 48%|████▊     | 96/200 [03:21<02:48,  1.62s/it]\n 48%|████▊     | 97/200 [03:22<02:05,  1.22s/it]\n 49%|████▉     | 98/200 [03:22<01:34,  1.08it/s]\n 50%|████▉     | 99/200 [03:25<02:48,  1.67s/it]\n 50%|█████     | 100/200 [03:29<03:38,  2.18s/it]\n 50%|█████     | 101/200 [03:29<02:38,  1.61s/it]\n 51%|█████     | 102/200 [03:29<01:57,  1.20s/it]\n 52%|█████▏    | 103/200 [03:33<03:01,  1.87s/it]\n 52%|█████▏    | 104/200 [03:33<02:13,  1.39s/it]\n 52%|█████▎    | 105/200 [03:33<01:41,  1.06s/it]\n 53%|█████▎    | 106/200 [03:33<01:18,  1.20it/s]\n 54%|█████▎    | 107/200 [03:34<01:02,  1.48it/s]\n 54%|█████▍    | 108/200 [03:34<00:46,  1.96it/s]\n 55%|█████▍    | 109/200 [03:34<00:40,  2.26it/s]\n 55%|█████▌    | 110/200 [03:38<01:59,  1.33s/it]\n 56%|█████▌    | 111/200 [03:41<02:53,  1.95s/it]\n 56%|█████▌    | 112/200 [03:41<02:06,  1.44s/it]\n 56%|█████▋    | 113/200 [03:45<02:57,  2.04s/it]\n 57%|█████▋    | 114/200 [03:48<03:34,  2.50s/it]\n 57%|█████▊    | 115/200 [03:52<03:52,  2.74s/it]\n 58%|█████▊    | 116/200 [03:55<04:07,  2.95s/it]\n 58%|█████▊    | 117/200 [03:58<04:15,  3.08s/it]\n 59%|█████▉    | 118/200 [04:02<04:22,  3.20s/it]\n 60%|█████▉    | 119/200 [04:02<03:04,  2.28s/it]\n 60%|██████    | 120/200 [04:06<03:36,  2.71s/it]\n 60%|██████    | 121/200 [04:06<02:32,  1.93s/it]\n 61%|██████    | 122/200 [04:06<01:51,  1.43s/it]\n 62%|██████▏   | 123/200 [04:09<02:35,  2.02s/it]\n 62%|██████▏   | 124/200 [04:13<03:06,  2.46s/it]\n 62%|██████▎   | 125/200 [04:13<02:11,  1.76s/it]\n 63%|██████▎   | 126/200 [04:13<01:36,  1.31s/it]\n 64%|██████▎   | 127/200 [04:14<01:12,  1.00it/s]\n 64%|██████▍   | 128/200 [04:17<02:04,  1.73s/it]\n 64%|██████▍   | 129/200 [04:20<02:38,  2.23s/it]\n 65%|██████▌   | 130/200 [04:21<01:54,  1.64s/it]\n 66%|██████▌   | 131/200 [04:21<01:24,  1.23s/it]\n 66%|██████▌   | 132/200 [04:24<02:07,  1.88s/it]\n 66%|██████▋   | 133/200 [04:28<02:36,  2.34s/it]\n 67%|██████▋   | 134/200 [04:31<02:57,  2.70s/it]\n 68%|██████▊   | 135/200 [04:35<03:08,  2.90s/it]\n 68%|██████▊   | 136/200 [04:35<02:12,  2.07s/it]\n 68%|██████▊   | 137/200 [04:35<01:36,  1.54s/it]\n 69%|██████▉   | 138/200 [04:39<02:10,  2.11s/it]\n 70%|██████▉   | 139/200 [04:39<01:34,  1.55s/it]\n 70%|███████   | 140/200 [04:42<02:08,  2.14s/it]\n 70%|███████   | 141/200 [04:46<02:28,  2.52s/it]\n 71%|███████   | 142/200 [04:49<02:42,  2.80s/it]\n 72%|███████▏  | 143/200 [04:53<02:49,  2.98s/it]\n 72%|███████▏  | 144/200 [04:56<02:51,  3.06s/it]\n 72%|███████▎  | 145/200 [04:59<02:57,  3.23s/it]\n 73%|███████▎  | 146/200 [05:03<02:59,  3.32s/it]\n 74%|███████▎  | 147/200 [05:06<02:56,  3.32s/it]\n 74%|███████▍  | 148/200 [05:10<02:54,  3.36s/it]\n 74%|███████▍  | 149/200 [05:13<02:52,  3.39s/it]\n 75%|███████▌  | 150/200 [05:13<02:00,  2.41s/it]\n 76%|███████▌  | 151/200 [05:17<02:12,  2.70s/it]\n 76%|███████▌  | 152/200 [05:17<01:34,  1.97s/it]\n 76%|███████▋  | 153/200 [05:20<01:54,  2.43s/it]\n 77%|███████▋  | 154/200 [05:24<02:07,  2.76s/it]\n 78%|███████▊  | 155/200 [05:24<01:28,  1.97s/it]\n 78%|███████▊  | 156/200 [05:28<01:45,  2.40s/it]\n 78%|███████▊  | 157/200 [05:31<01:58,  2.76s/it]\n 79%|███████▉  | 158/200 [05:31<01:22,  1.97s/it]\n 80%|███████▉  | 159/200 [05:32<00:59,  1.46s/it]\n 80%|████████  | 160/200 [05:35<01:21,  2.04s/it]\n 80%|████████  | 161/200 [05:38<01:34,  2.43s/it]\n 81%|████████  | 162/200 [05:42<01:43,  2.73s/it]\n 82%|████████▏ | 163/200 [05:45<01:49,  2.96s/it]\n 82%|████████▏ | 164/200 [05:49<01:51,  3.10s/it]\n 82%|████████▎ | 165/200 [05:49<01:17,  2.21s/it]\n 83%|████████▎ | 166/200 [05:52<01:26,  2.55s/it]\n 84%|████████▎ | 167/200 [05:56<01:33,  2.85s/it]\n 84%|████████▍ | 168/200 [05:59<01:37,  3.03s/it]\n 84%|████████▍ | 169/200 [06:02<01:37,  3.14s/it]\n 85%|████████▌ | 170/200 [06:06<01:36,  3.21s/it]\n 86%|████████▌ | 171/200 [06:06<01:06,  2.28s/it]\n 86%|████████▌ | 172/200 [06:10<01:14,  2.66s/it]\n 86%|████████▋ | 173/200 [06:10<00:51,  1.90s/it]\n 87%|████████▋ | 174/200 [06:13<01:02,  2.42s/it]\n 88%|████████▊ | 175/200 [06:17<01:07,  2.71s/it]\n 88%|████████▊ | 176/200 [06:20<01:10,  2.92s/it]\n 88%|████████▊ | 177/200 [06:20<00:47,  2.08s/it]\n 89%|████████▉ | 178/200 [06:24<00:55,  2.51s/it]\n 90%|████████▉ | 179/200 [06:27<00:58,  2.77s/it]\n 90%|█████████ | 180/200 [06:30<00:58,  2.90s/it]\n 90%|█████████ | 181/200 [06:34<00:58,  3.08s/it]\n 91%|█████████ | 182/200 [06:34<00:39,  2.19s/it]\n 92%|█████████▏| 183/200 [06:34<00:27,  1.62s/it]\n 92%|█████████▏| 184/200 [06:38<00:34,  2.15s/it]\n 92%|█████████▎| 185/200 [06:41<00:37,  2.51s/it]\n 93%|█████████▎| 186/200 [06:45<00:39,  2.83s/it]\n 94%|█████████▎| 187/200 [06:45<00:26,  2.02s/it]\n 94%|█████████▍| 188/200 [06:48<00:29,  2.43s/it]\n 94%|█████████▍| 189/200 [06:48<00:19,  1.78s/it]\n 95%|█████████▌| 190/200 [06:49<00:13,  1.32s/it]\n 96%|█████████▌| 191/200 [06:52<00:17,  1.93s/it]\n 96%|█████████▌| 192/200 [06:55<00:18,  2.37s/it]\n 96%|█████████▋| 193/200 [06:56<00:12,  1.73s/it]\n 97%|█████████▋| 194/200 [06:59<00:13,  2.27s/it]\n 98%|█████████▊| 195/200 [07:03<00:13,  2.63s/it]\n 98%|█████████▊| 196/200 [07:06<00:11,  2.85s/it]\n 98%|█████████▊| 197/200 [07:06<00:06,  2.04s/it]\n 99%|█████████▉| 198/200 [07:06<00:03,  1.51s/it]\n100%|█████████▉| 199/200 [07:07<00:01,  1.13s/it]\n100%|██████████| 200/200 [07:10<00:00,  1.80s/it]\n100%|██████████| 200/200 [07:10<00:00,  2.15s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1750830070/profiles.py", line 621, in <module>\n    cli()\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n    return self.main(*args, **kwargs)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n    rv = self.invoke(ctx)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n    return _process_result(sub_ctx.command.invoke(sub_ctx))\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n    return ctx.invoke(self.callback, **ctx.params)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n    return __callback(*args, **kwargs)\n  File "/code/chaiverse_profiler_1750830070/profiles.py", line 112, in profile_batches\n    profiles = run_batch_profile_with_auto_batch(target, batches, settings, auto_batch, output)\n  File "/code/chaiverse_profiler_1750830070/profiles.py", line 163, in run_batch_profile_with_auto_batch\n    profiles = run_batch_profile(target, batches, settings, output)\n  File "/code/chaiverse_profiler_1750830070/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 430.4358241558075\nerrors 80\nmean length: 1.8\n\nthroughput (request / second): 0.4646453403181534\nthroughput (character / second): 0.836361612572676\naverage request duration (s) 2.152063068151474\n50%ile request duration (s) 3.375891327857971\n75%ile request duration (s) 3.4378647208213806\n90%ile request duration (s) 3.5255215406417846\n95%ile request duration (s) 3.5598811149597163\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-81771-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-81771-v1-profiler
Service chaiml-llama8b-retune7-81771-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.33s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-81771-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-retune7-81771-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-81771-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-81771-v1-profiler ready after 141.2146098613739s
Pipeline stage MKMLProfilerDeployer completed in 141.79s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc:/code/chaiverse_profiler_1750830716 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750830716 && 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_1750830716/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc:/code/chaiverse_profiler_1750831122 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750831122 && 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_1750831122/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc:/code/chaiverse_profiler_1750831536 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retun9c281ac8f10244d1aaf95a934bd4c190-deplommznc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750831536 && 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_1750831536/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n  0%|          | 0/200 [00:00<?, ?it/s]\n  0%|          | 1/200 [00:03<11:23,  3.43s/it]\n  1%|          | 2/200 [00:06<11:14,  3.40s/it]\n  2%|▏         | 3/200 [00:10<11:03,  3.37s/it]\n  2%|▏         | 4/200 [00:10<06:49,  2.09s/it]\n  2%|▎         | 5/200 [00:13<08:22,  2.58s/it]\n  3%|▎         | 6/200 [00:13<05:37,  1.74s/it]\n  4%|▎         | 7/200 [00:14<04:02,  1.25s/it]\n  4%|▍         | 8/200 [00:14<02:59,  1.07it/s]\n  4%|▍         | 9/200 [00:17<05:21,  1.68s/it]\n  5%|▌         | 10/200 [00:21<06:57,  2.20s/it]\n  6%|▌         | 11/200 [00:21<05:02,  1.60s/it]\n  6%|▌         | 12/200 [00:21<03:43,  1.19s/it]\n  6%|▋         | 13/200 [00:21<02:48,  1.11it/s]\n  7%|▋         | 14/200 [00:25<05:05,  1.64s/it]\n  8%|▊         | 15/200 [00:25<03:45,  1.22s/it]\n  8%|▊         | 16/200 [00:25<02:50,  1.08it/s]\n  8%|▊         | 17/200 [00:25<02:13,  1.37it/s]\n  9%|▉         | 18/200 [00:29<04:36,  1.52s/it]\n 10%|▉         | 19/200 [00:32<06:13,  2.06s/it]\n 10%|█         | 20/200 [00:35<07:24,  2.47s/it]\n 10%|█         | 21/200 [00:39<08:13,  2.76s/it]\n 11%|█         | 22/200 [00:39<05:49,  1.97s/it]\n 12%|█▏        | 23/200 [00:39<04:17,  1.45s/it]\n 12%|█▏        | 24/200 [00:43<05:58,  2.04s/it]\n 12%|█▎        | 25/200 [00:43<04:22,  1.50s/it]\n 13%|█▎        | 26/200 [00:43<03:16,  1.13s/it]\n 14%|█▎        | 27/200 [00:43<02:30,  1.15it/s]\n 14%|█▍        | 28/200 [00:47<04:37,  1.61s/it]\n 14%|█▍        | 29/200 [00:50<06:06,  2.14s/it]\n 15%|█▌        | 30/200 [00:54<07:07,  2.51s/it]\n 16%|█▌        | 31/200 [00:54<05:09,  1.83s/it]\n 16%|█▌        | 32/200 [00:57<06:24,  2.29s/it]\n 16%|█▋        | 33/200 [00:57<04:39,  1.67s/it]\n 17%|█▋        | 34/200 [01:01<06:02,  2.18s/it]\n 18%|█▊        | 35/200 [01:04<07:01,  2.55s/it]\n 18%|█▊        | 36/200 [01:08<07:40,  2.81s/it]\n 18%|█▊        | 37/200 [01:11<08:06,  2.98s/it]\n 19%|█▉        | 38/200 [01:11<05:50,  2.16s/it]\n 20%|█▉        | 39/200 [01:11<04:16,  1.59s/it]\n 20%|██        | 40/200 [01:12<03:09,  1.19s/it]\n 20%|██        | 41/200 [01:12<02:25,  1.09it/s]\n 21%|██        | 42/200 [01:12<01:46,  1.48it/s]\n 22%|██▏       | 43/200 [01:16<03:58,  1.52s/it]\n 22%|██▏       | 44/200 [01:19<05:22,  2.07s/it]\n 22%|██▎       | 45/200 [01:22<06:21,  2.46s/it]\n 23%|██▎       | 46/200 [01:22<04:31,  1.76s/it]\n 24%|██▎       | 47/200 [01:23<03:19,  1.30s/it]\n 24%|██▍       | 48/200 [01:23<02:29,  1.02it/s]\n 24%|██▍       | 49/200 [01:23<01:54,  1.31it/s]\n 25%|██▌       | 50/200 [01:27<03:51,  1.54s/it]\n 26%|██▌       | 51/200 [01:27<02:51,  1.15s/it]\n 26%|██▌       | 52/200 [01:30<04:26,  1.80s/it]\n 26%|██▋       | 53/200 [01:33<05:34,  2.28s/it]\n 27%|██▋       | 54/200 [01:37<06:24,  2.64s/it]\n 28%|██▊       | 55/200 [01:37<04:37,  1.92s/it]\n 28%|██▊       | 56/200 [01:41<05:43,  2.39s/it]\n 28%|██▊       | 57/200 [01:44<06:26,  2.70s/it]\n 29%|██▉       | 58/200 [01:47<06:51,  2.89s/it]\n 30%|██▉       | 59/200 [01:51<07:05,  3.02s/it]\n 30%|███       | 60/200 [01:54<07:15,  3.11s/it]\n 30%|███       | 61/200 [01:57<07:23,  3.19s/it]\n 31%|███       | 62/200 [01:58<05:17,  2.30s/it]\n 32%|███▏      | 63/200 [02:01<05:56,  2.61s/it]\n 32%|███▏      | 64/200 [02:04<06:26,  2.84s/it]\n 32%|███▎      | 65/200 [02:08<06:44,  3.00s/it]\n 33%|███▎      | 66/200 [02:08<04:50,  2.17s/it]\n 34%|███▎      | 67/200 [02:08<03:32,  1.60s/it]\n 34%|███▍      | 68/200 [02:12<04:40,  2.12s/it]\n 34%|███▍      | 69/200 [02:12<03:23,  1.56s/it]\n 35%|███▌      | 70/200 [02:15<04:33,  2.11s/it]\n 36%|███▌      | 71/200 [02:19<05:19,  2.47s/it]\n 36%|███▌      | 72/200 [02:19<03:51,  1.80s/it]\n 36%|███▋      | 73/200 [02:19<02:45,  1.30s/it]\n 37%|███▋      | 74/200 [02:19<02:04,  1.01it/s]\n 38%|███▊      | 75/200 [02:23<03:31,  1.69s/it]\n 38%|███▊      | 76/200 [02:26<04:38,  2.24s/it]\n 38%|███▊      | 77/200 [02:26<03:17,  1.61s/it]\n 39%|███▉      | 78/200 [02:26<02:25,  1.20s/it]\n 40%|███▉      | 79/200 [02:30<03:44,  1.85s/it]\n 40%|████      | 80/200 [02:33<04:41,  2.34s/it]\n 40%|████      | 81/200 [02:33<03:19,  1.68s/it]\n 41%|████      | 82/200 [02:34<02:26,  1.25s/it]\n 42%|████▏     | 83/200 [02:37<03:40,  1.88s/it]\n 42%|████▏     | 84/200 [02:40<04:29,  2.33s/it]\n 42%|████▎     | 85/200 [02:44<05:05,  2.66s/it]\n 43%|████▎     | 86/200 [02:44<03:36,  1.90s/it]\n 44%|████▎     | 87/200 [02:44<02:38,  1.40s/it]\n 44%|████▍     | 88/200 [02:48<03:43,  1.99s/it]\n 44%|████▍     | 89/200 [02:51<04:25,  2.40s/it]\n 45%|████▌     | 90/200 [02:54<05:00,  2.74s/it]\n 46%|████▌     | 91/200 [02:55<03:32,  1.95s/it]\n 46%|████▌     | 92/200 [02:55<02:35,  1.44s/it]\n 46%|████▋     | 93/200 [02:58<03:37,  2.03s/it]\n 47%|████▋     | 94/200 [03:02<04:17,  2.43s/it]\n 48%|████▊     | 95/200 [03:05<04:44,  2.71s/it]\n 48%|████▊     | 96/200 [03:05<03:21,  1.94s/it]\n 48%|████▊     | 97/200 [03:05<02:27,  1.43s/it]\n 49%|████▉     | 98/200 [03:06<01:50,  1.09s/it]\n 50%|████▉     | 99/200 [03:06<01:24,  1.20it/s]\n 50%|█████     | 100/200 [03:09<02:38,  1.58s/it]\n 50%|█████     | 101/200 [03:12<03:28,  2.10s/it]\n 51%|█████     | 102/200 [03:13<02:31,  1.54s/it]\n 52%|█████▏    | 103/200 [03:16<03:22,  2.08s/it]\n 52%|█████▏    | 104/200 [03:16<02:26,  1.53s/it]\n 52%|█████▎    | 105/200 [03:17<01:48,  1.14s/it]\n 53%|█████▎    | 106/200 [03:17<01:21,  1.15it/s]\n 54%|█████▎    | 107/200 [03:20<02:30,  1.62s/it]\n 54%|█████▍    | 108/200 [03:24<03:18,  2.15s/it]\n 55%|█████▍    | 109/200 [03:24<02:20,  1.54s/it]\n 55%|█████▌    | 110/200 [03:27<03:10,  2.12s/it]\n 56%|█████▌    | 111/200 [03:27<02:15,  1.52s/it]\n 56%|█████▌    | 112/200 [03:31<03:01,  2.06s/it]\n 56%|█████▋    | 113/200 [03:34<03:34,  2.46s/it]\n 57%|█████▋    | 114/200 [03:37<03:55,  2.74s/it]\n 57%|█████▊    | 115/200 [03:37<02:46,  1.95s/it]\n 58%|█████▊    | 116/200 [03:41<03:22,  2.41s/it]\n 58%|█████▊    | 117/200 [03:41<02:23,  1.72s/it]\n 59%|█████▉    | 118/200 [03:41<01:44,  1.28s/it]\n 60%|█████▉    | 119/200 [03:42<01:18,  1.04it/s]\n 60%|██████    | 120/200 [03:45<02:17,  1.72s/it]\n 60%|██████    | 121/200 [03:45<01:40,  1.27s/it]\n 61%|██████    | 122/200 [03:49<02:27,  1.89s/it]\n 62%|██████▏   | 123/200 [03:49<01:48,  1.41s/it]\n 62%|██████▏   | 124/200 [03:52<02:31,  1.99s/it]\n 62%|██████▎   | 125/200 [03:56<03:00,  2.41s/it]\n 63%|██████▎   | 126/200 [03:56<02:10,  1.76s/it]\n 64%|██████▎   | 127/200 [03:56<01:35,  1.31s/it]\n 64%|██████▍   | 128/200 [03:59<02:18,  1.93s/it]\n 64%|██████▍   | 129/200 [04:03<02:47,  2.35s/it]\n 65%|██████▌   | 130/200 [04:06<03:07,  2.68s/it]\n 66%|██████▌   | 131/200 [04:10<03:19,  2.90s/it]\n 66%|██████▌   | 132/200 [04:10<02:22,  2.10s/it]\n 66%|██████▋   | 133/200 [04:10<01:43,  1.54s/it]\n 67%|██████▋   | 134/200 [04:13<02:17,  2.08s/it]\n 68%|██████▊   | 135/200 [04:17<02:40,  2.46s/it]\n 68%|██████▊   | 136/200 [04:20<02:54,  2.72s/it]\n 68%|██████▊   | 137/200 [04:24<03:03,  2.91s/it]\n 69%|██████▉   | 138/200 [04:24<02:08,  2.08s/it]\n 70%|██████▉   | 139/200 [04:24<01:33,  1.53s/it]\n 70%|███████   | 140/200 [04:27<02:03,  2.06s/it]\n 70%|███████   | 141/200 [04:27<01:29,  1.51s/it]\n 71%|███████   | 142/200 [04:28<01:05,  1.13s/it]\n 72%|███████▏  | 143/200 [04:31<01:42,  1.81s/it]\n 72%|███████▏  | 144/200 [04:31<01:14,  1.33s/it]\n 72%|███████▎  | 145/200 [04:32<00:55,  1.01s/it]\n 73%|███████▎  | 146/200 [04:32<00:42,  1.28it/s]\n 74%|███████▎  | 147/200 [04:35<01:23,  1.57s/it]\n 74%|███████▍  | 148/200 [04:35<01:01,  1.18s/it]\n 74%|███████▍  | 149/200 [04:36<00:43,  1.16it/s]\n 75%|███████▌  | 150/200 [04:39<01:24,  1.69s/it]\n 76%|███████▌  | 151/200 [04:43<01:47,  2.19s/it]\n 76%|███████▌  | 152/200 [04:46<02:02,  2.56s/it]\n 76%|███████▋  | 153/200 [04:46<01:25,  1.82s/it]\n 77%|███████▋  | 154/200 [04:46<01:02,  1.35s/it]\n 78%|███████▊  | 155/200 [04:50<01:28,  1.96s/it]\n 78%|███████▊  | 156/200 [04:53<01:43,  2.36s/it]\n 78%|███████▊  | 157/200 [04:56<01:55,  2.68s/it]\n 79%|███████▉  | 158/200 [05:00<02:01,  2.88s/it]\n 80%|███████▉  | 159/200 [05:03<02:03,  3.02s/it]\n 80%|████████  | 160/200 [05:03<01:26,  2.15s/it]\n 80%|████████  | 161/200 [05:03<01:01,  1.58s/it]\n 81%|████████  | 162/200 [05:07<01:21,  2.15s/it]\n 82%|████████▏ | 163/200 [05:10<01:34,  2.54s/it]\n 82%|████████▏ | 164/200 [05:14<01:41,  2.81s/it]\n 82%|████████▎ | 165/200 [05:17<01:43,  2.94s/it]\n 83%|████████▎ | 166/200 [05:17<01:11,  2.10s/it]\n 84%|████████▎ | 167/200 [05:21<01:22,  2.51s/it]\n 84%|████████▍ | 168/200 [05:21<00:57,  1.79s/it]\n 84%|████████▍ | 169/200 [05:24<01:10,  2.28s/it]\n 85%|████████▌ | 170/200 [05:28<01:18,  2.62s/it]\n 86%|████████▌ | 171/200 [05:31<01:23,  2.87s/it]\n 86%|████████▌ | 172/200 [05:31<00:57,  2.04s/it]\n 86%|████████▋ | 173/200 [05:31<00:40,  1.50s/it]\n 87%|████████▋ | 174/200 [05:35<00:54,  2.08s/it]\n 88%|████████▊ | 175/200 [05:38<01:02,  2.51s/it]\n 88%|████████▊ | 176/200 [05:39<00:42,  1.79s/it]\n 88%|████████▊ | 177/200 [05:39<00:30,  1.34s/it]\n 89%|████████▉ | 178/200 [05:39<00:22,  1.02s/it]\n 90%|████████▉ | 179/200 [05:42<00:35,  1.71s/it]\n 90%|█████████ | 180/200 [05:43<00:25,  1.26s/it]\n 90%|█████████ | 181/200 [05:46<00:36,  1.91s/it]\n 91%|█████████ | 182/200 [05:49<00:42,  2.35s/it]\n 92%|█████████▏| 183/200 [05:53<00:45,  2.69s/it]\n 92%|█████████▏| 184/200 [05:56<00:46,  2.89s/it]\n 92%|█████████▎| 185/200 [06:00<00:45,  3.04s/it]\n 93%|█████████▎| 186/200 [06:00<00:30,  2.16s/it]\n 94%|█████████▎| 187/200 [06:03<00:33,  2.56s/it]\n 94%|█████████▍| 188/200 [06:07<00:33,  2.80s/it]\n 94%|█████████▍| 189/200 [06:07<00:21,  2.00s/it]\n 95%|█████████▌| 190/200 [06:10<00:24,  2.44s/it]\n 96%|█████████▌| 191/200 [06:10<00:15,  1.78s/it]\n 96%|█████████▌| 192/200 [06:11<00:10,  1.31s/it]\n 96%|█████████▋| 193/200 [06:14<00:13,  1.93s/it]\n 97%|█████████▋| 194/200 [06:17<00:14,  2.34s/it]\n 98%|█████████▊| 195/200 [06:21<00:13,  2.67s/it]\n 98%|█████████▊| 196/200 [06:24<00:11,  2.83s/it]\n 98%|█████████▊| 197/200 [06:27<00:09,  3.01s/it]\n 99%|█████████▉| 198/200 [06:31<00:06,  3.10s/it]\n100%|█████████▉| 199/200 [06:31<00:02,  2.21s/it]\n100%|██████████| 200/200 [06:34<00:00,  2.54s/it]\n100%|██████████| 200/200 [06:34<00:00,  1.97s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1750831536/profiles.py", line 621, in <module>\n    cli()\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__\n    return self.main(*args, **kwargs)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main\n    rv = self.invoke(ctx)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke\n    return _process_result(sub_ctx.command.invoke(sub_ctx))\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke\n    return ctx.invoke(self.callback, **ctx.params)\n  File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke\n    return __callback(*args, **kwargs)\n  File "/code/chaiverse_profiler_1750831536/profiles.py", line 112, in profile_batches\n    profiles = run_batch_profile_with_auto_batch(target, batches, settings, auto_batch, output)\n  File "/code/chaiverse_profiler_1750831536/profiles.py", line 163, in run_batch_profile_with_auto_batch\n    profiles = run_batch_profile(target, batches, settings, output)\n  File "/code/chaiverse_profiler_1750831536/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 394.6726322174072\nerrors 89\nmean length: 1.665\n\nthroughput (request / second): 0.5067490970334855\nthroughput (character / second): 0.8437372465607532\naverage request duration (s) 1.973263260126114\n50%ile request duration (s) 3.321436882019043\n75%ile request duration (s) 3.385994553565979\n90%ile request duration (s) 3.4393285512924194\n95%ile request duration (s) 3.4817227125167847\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-81771-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-81771-v1-profiler
Service chaiml-llama8b-retune7-81771-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.27s
Shutdown handler de-registered
chaiml-llama8b-retune7-_81771_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-retune7-_81771_v1 status is now torndown due to DeploymentManager action