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-llama3-200m-v2-t-76584-v4-mkmlizer
Waiting for job on chaiml-llama3-200m-v2-t-76584-v4-mkmlizer to finish
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-daren-god-of-deat_6797_v1: HTTPConnectionPool(host='chaiml-daren-god-of-deat-6797-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-isaac-brown-sylu_53639_v2: HTTPConnectionPool(host='chaiml-isaac-brown-sylu-53639-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: Downloaded to shared memory in 28.685s
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: Checking if ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725 already exists in ChaiML
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpoejnhy2i, device:0
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia/config.json
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia/special_tokens_map.json
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia/tokenizer_config.json
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia/tokenizer.json
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v4/nvidia/flywheel_model.0.safetensors
chaiml-llama3-200m-v2-t-76584-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.28it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.57it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 47.10it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 46.13it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 52.22it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.63it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.20it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 48.48it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 44.24it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 43.52it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 47.54it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 46.60it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 46.30it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 47.09it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 25.59it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 34.23it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:05, 35.43it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:05, 37.11it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 43.11it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 41.67it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 40.87it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:03, 45.86it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 43.50it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 42.90it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 48.42it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 45.10it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 44.55it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 49.81it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:02, 43.51it/s]
Loading 0:  61%|██████    | 177/291 [00:04<00:02, 44.97it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 43.62it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 30.57it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.05it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 32.37it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 37.49it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 39.25it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 39.42it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 38.15it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 36.10it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 43.69it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 43.52it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 43.85it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 40.93it/s]
Loading 0:  86%|████████▌ | 249/291 [00:06<00:01, 40.86it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 45.52it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 44.19it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 43.97it/s]
Loading 0:  93%|█████████▎| 270/291 [00:06<00:00, 45.12it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 36.19it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 41.58it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 36.94it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 31.00it/s]
                                                            
Job chaiml-llama3-200m-v2-t-76584-v4-mkmlizer completed after 522.28s with status: succeeded
Stopping job with name chaiml-llama3-200m-v2-t-76584-v4-mkmlizer
Pipeline stage MKMLizer completed in 522.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v4
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v4 to be ready
Failed to get response for submission chaiml-bat-boys-azeril-_87348_v1: ('http://chaiml-bat-boys-azeril-87348-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission chaiml-llama31-mer-v2-t_44570_v2: HTTPConnectionPool(host='chaiml-llama31-mer-v2-t-44570-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama3-200m-v2-t-76584-v4 ready after 322.0779883861542s
Pipeline stage MKMLDeployer completed in 323.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3774333000183105s
Received healthy response to inference request in 2.728858232498169s
Received healthy response to inference request in 3.7125566005706787s
Received healthy response to inference request in 3.718252658843994s
Received healthy response to inference request in 4.214011192321777s
5 requests
0 failed requests
5th percentile: 2.858573246002197
10th percentile: 2.9882882595062257
20th percentile: 3.2477182865142824
30th percentile: 3.4444579601287844
40th percentile: 3.5785072803497315
50th percentile: 3.7125566005706787
60th percentile: 3.714835023880005
70th percentile: 3.7171134471893312
80th percentile: 3.817404365539551
90th percentile: 4.015707778930664
95th percentile: 4.114859485626221
99th percentile: 4.194180850982666
mean time: 3.550222396850586
Pipeline stage StressChecker completed in 19.09s
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 0.98s
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 0.72s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v4-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v4-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v4-profiler ready after 324.29282879829407s
Pipeline stage MKMLProfilerDeployer completed in 325.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv:/code/chaiverse_profiler_1752855515 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752855515 && 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_1752855515/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv:/code/chaiverse_profiler_1752855954 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752855954 && 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_1752855954/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv:/code/chaiverse_profiler_1752856402 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplocgvsv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752856402 && 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_1752856402/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<11:12,  3.38s/it]\n  1%|          | 2/200 [00:03<05:07,  1.55s/it]\n  2%|▏         | 3/200 [00:03<03:09,  1.04it/s]\n  2%|▏         | 4/200 [00:07<06:32,  2.00s/it]\n  2%|▎         | 5/200 [00:11<08:31,  2.62s/it]\n  3%|▎         | 6/200 [00:14<09:29,  2.93s/it]\n  4%|▎         | 7/200 [00:14<06:28,  2.01s/it]\n  4%|▍         | 8/200 [00:18<08:13,  2.57s/it]\n  4%|▍         | 9/200 [00:18<05:44,  1.80s/it]\n  5%|▌         | 10/200 [00:22<07:32,  2.38s/it]\n  6%|▌         | 11/200 [00:22<05:19,  1.69s/it]\n  6%|▌         | 12/200 [00:22<03:55,  1.25s/it]\n  6%|▋         | 13/200 [00:26<06:07,  1.96s/it]\n  7%|▋         | 14/200 [00:30<07:42,  2.49s/it]\n  8%|▊         | 15/200 [00:30<05:27,  1.77s/it]\n  8%|▊         | 16/200 [00:33<07:15,  2.36s/it]\n  8%|▊         | 17/200 [00:37<08:21,  2.74s/it]\n  9%|▉         | 18/200 [00:41<09:05,  3.00s/it]\n 10%|▉         | 19/200 [00:44<09:32,  3.16s/it]\n 10%|█         | 20/200 [00:44<06:45,  2.25s/it]\n 10%|█         | 21/200 [00:48<07:56,  2.66s/it]\n 11%|█         | 22/200 [00:52<08:42,  2.94s/it]\n 12%|█▏        | 23/200 [00:55<09:21,  3.17s/it]\n 12%|█▏        | 24/200 [00:59<09:42,  3.31s/it]\n 12%|█▎        | 25/200 [00:59<06:51,  2.35s/it]\n 13%|█▎        | 26/200 [01:03<07:51,  2.71s/it]\n 14%|█▎        | 27/200 [01:03<05:41,  1.97s/it]\n 14%|█▍        | 28/200 [01:03<04:10,  1.46s/it]\n 14%|█▍        | 29/200 [01:07<06:00,  2.11s/it]\n 15%|█▌        | 30/200 [01:07<04:23,  1.55s/it]\n 16%|█▌        | 31/200 [01:07<03:16,  1.16s/it]\n 16%|█▌        | 32/200 [01:07<02:29,  1.12it/s]\n 16%|█▋        | 33/200 [01:08<01:57,  1.42it/s]\n 17%|█▋        | 34/200 [01:08<01:35,  1.74it/s]\n 18%|█▊        | 35/200 [01:12<04:04,  1.48s/it]\n 18%|█▊        | 36/200 [01:15<05:46,  2.11s/it]\n 18%|█▊        | 37/200 [01:15<04:14,  1.56s/it]\n 19%|█▉        | 38/200 [01:19<05:53,  2.18s/it]\n 20%|█▉        | 39/200 [01:19<04:18,  1.61s/it]\n 20%|██        | 40/200 [01:20<03:06,  1.16s/it]\n 20%|██        | 41/200 [01:20<02:22,  1.11it/s]\n 21%|██        | 42/200 [01:23<04:29,  1.70s/it]\n 22%|██▏       | 43/200 [01:24<03:19,  1.27s/it]\n 22%|██▏       | 44/200 [01:24<02:31,  1.03it/s]\n 22%|██▎       | 45/200 [01:24<01:57,  1.32it/s]\n 23%|██▎       | 46/200 [01:28<04:09,  1.62s/it]\n 24%|██▎       | 47/200 [01:28<03:05,  1.21s/it]\n 24%|██▍       | 48/200 [01:32<04:52,  1.93s/it]\n 24%|██▍       | 49/200 [01:32<03:34,  1.42s/it]\n 25%|██▌       | 50/200 [01:35<05:10,  2.07s/it]\n 26%|██▌       | 51/200 [01:36<03:47,  1.52s/it]\n 26%|██▌       | 52/200 [01:39<05:17,  2.15s/it]\n 26%|██▋       | 53/200 [01:43<06:22,  2.60s/it]\n 27%|██▋       | 54/200 [01:43<04:36,  1.90s/it]\n 28%|██▊       | 55/200 [01:43<03:24,  1.41s/it]\n 28%|██▊       | 56/200 [01:44<02:33,  1.06s/it]\n 28%|██▊       | 57/200 [01:47<04:21,  1.83s/it]\n 29%|██▉       | 58/200 [01:51<05:34,  2.35s/it]\n 30%|██▉       | 59/200 [01:51<03:57,  1.68s/it]\n 30%|███       | 60/200 [01:51<02:56,  1.26s/it]\n 30%|███       | 61/200 [01:55<04:32,  1.96s/it]\n 31%|███       | 62/200 [01:59<05:43,  2.49s/it]\n 32%|███▏      | 63/200 [01:59<04:03,  1.78s/it]\n 32%|███▏      | 64/200 [02:02<05:19,  2.35s/it]\n 32%|███▎      | 65/200 [02:06<06:09,  2.73s/it]\n 33%|███▎      | 66/200 [02:06<04:21,  1.95s/it]\n 34%|███▎      | 67/200 [02:10<05:26,  2.45s/it]\n 34%|███▍      | 68/200 [02:13<06:06,  2.78s/it]\n 34%|███▍      | 69/200 [02:14<04:23,  2.01s/it]\n 35%|███▌      | 70/200 [02:17<05:23,  2.49s/it]\n 36%|███▌      | 71/200 [02:17<03:54,  1.82s/it]\n 36%|███▌      | 72/200 [02:21<05:06,  2.40s/it]\n 36%|███▋      | 73/200 [02:21<03:37,  1.72s/it]\n 37%|███▋      | 74/200 [02:25<04:51,  2.32s/it]\n 38%|███▊      | 75/200 [02:25<03:27,  1.66s/it]\n 38%|███▊      | 76/200 [02:29<04:42,  2.28s/it]\n 38%|███▊      | 77/200 [02:29<03:20,  1.63s/it]\n 39%|███▉      | 78/200 [02:29<02:29,  1.22s/it]\n 40%|███▉      | 79/200 [02:33<03:56,  1.95s/it]\n 40%|████      | 80/200 [02:33<02:52,  1.44s/it]\n 40%|████      | 81/200 [02:33<02:09,  1.09s/it]\n 41%|████      | 82/200 [02:37<03:39,  1.86s/it]\n 42%|████▏     | 83/200 [02:37<02:40,  1.38s/it]\n 42%|████▏     | 84/200 [02:41<03:57,  2.05s/it]\n 42%|████▎     | 85/200 [02:45<04:53,  2.55s/it]\n 43%|████▎     | 86/200 [02:45<03:27,  1.82s/it]\n 44%|████▎     | 87/200 [02:48<04:28,  2.38s/it]\n 44%|████▍     | 88/200 [02:52<05:10,  2.77s/it]\n 44%|████▍     | 89/200 [02:52<03:39,  1.98s/it]\n 45%|████▌     | 90/200 [02:56<04:31,  2.47s/it]\n 46%|████▌     | 91/200 [03:00<05:10,  2.85s/it]\n 46%|████▌     | 92/200 [03:00<03:39,  2.03s/it]\n 46%|████▋     | 93/200 [03:04<04:34,  2.57s/it]\n 47%|████▋     | 94/200 [03:07<05:07,  2.90s/it]\n 48%|████▊     | 95/200 [03:07<03:37,  2.07s/it]\n 48%|████▊     | 96/200 [03:11<04:25,  2.55s/it]\n 48%|████▊     | 97/200 [03:11<03:13,  1.88s/it]\n 49%|████▉     | 98/200 [03:15<04:10,  2.45s/it]\n 50%|████▉     | 99/200 [03:19<04:46,  2.84s/it]\n 50%|█████     | 100/200 [03:19<03:22,  2.03s/it]\n 50%|█████     | 101/200 [03:19<02:28,  1.50s/it]\n 51%|█████     | 102/200 [03:20<01:50,  1.13s/it]\n 52%|█████▏    | 103/200 [03:23<03:01,  1.88s/it]\n 52%|█████▏    | 104/200 [03:23<02:14,  1.40s/it]\n 52%|█████▎    | 105/200 [03:27<03:15,  2.06s/it]\n 53%|█████▎    | 106/200 [03:27<02:23,  1.53s/it]\n 54%|█████▎    | 107/200 [03:28<01:46,  1.15s/it]\n 54%|█████▍    | 108/200 [03:28<01:21,  1.12it/s]\n 55%|█████▍    | 109/200 [03:32<02:37,  1.73s/it]\n 55%|█████▌    | 110/200 [03:35<03:28,  2.31s/it]\n 56%|█████▌    | 111/200 [03:35<02:27,  1.66s/it]\n 56%|█████▌    | 112/200 [03:39<03:19,  2.26s/it]\n 56%|█████▋    | 113/200 [03:43<03:55,  2.71s/it]\n 57%|█████▋    | 114/200 [03:43<02:46,  1.93s/it]\n 57%|█████▊    | 115/200 [03:47<03:26,  2.43s/it]\n 58%|█████▊    | 116/200 [03:50<03:57,  2.83s/it]\n 58%|█████▊    | 117/200 [03:54<04:13,  3.05s/it]\n 59%|█████▉    | 118/200 [03:57<04:23,  3.22s/it]\n 60%|█████▉    | 119/200 [03:58<03:05,  2.29s/it]\n 60%|██████    | 120/200 [03:58<02:14,  1.69s/it]\n 60%|██████    | 121/200 [03:58<01:39,  1.26s/it]\n 61%|██████    | 122/200 [04:02<02:32,  1.96s/it]\n 62%|██████▏   | 123/200 [04:02<01:51,  1.44s/it]\n 62%|██████▏   | 124/200 [04:02<01:22,  1.09s/it]\n 62%|██████▎   | 125/200 [04:02<01:03,  1.19it/s]\n 63%|██████▎   | 126/200 [04:03<00:49,  1.49it/s]\n 64%|██████▎   | 127/200 [04:06<01:54,  1.56s/it]\n 64%|██████▍   | 128/200 [04:10<02:38,  2.20s/it]\n 64%|██████▍   | 129/200 [04:14<03:06,  2.62s/it]\n 65%|██████▌   | 130/200 [04:14<02:13,  1.91s/it]\n 66%|██████▌   | 131/200 [04:18<02:48,  2.44s/it]\n 66%|██████▌   | 132/200 [04:18<02:01,  1.79s/it]\n 66%|██████▋   | 133/200 [04:18<01:29,  1.34s/it]\n 67%|██████▋   | 134/200 [04:18<01:07,  1.02s/it]\n 68%|██████▊   | 135/200 [04:19<00:48,  1.33it/s]\n 68%|██████▊   | 136/200 [04:22<01:43,  1.61s/it]\n 68%|██████▊   | 137/200 [04:26<02:23,  2.27s/it]\n 69%|██████▉   | 138/200 [04:30<02:44,  2.65s/it]\n 70%|██████▉   | 139/200 [04:33<02:58,  2.93s/it]\n 70%|███████   | 140/200 [04:37<03:08,  3.15s/it]\n 70%|███████   | 141/200 [04:40<03:14,  3.29s/it]\n 71%|███████   | 142/200 [04:41<02:15,  2.34s/it]\n 72%|███████▏  | 143/200 [04:44<02:36,  2.75s/it]\n 72%|███████▏  | 144/200 [04:48<02:47,  3.00s/it]\n 72%|███████▎  | 145/200 [04:51<02:54,  3.18s/it]\n 73%|███████▎  | 146/200 [04:52<02:02,  2.26s/it]\n 74%|███████▎  | 147/200 [04:52<01:28,  1.66s/it]\n 74%|███████▍  | 148/200 [04:52<01:04,  1.24s/it]\n 74%|███████▍  | 149/200 [04:52<00:48,  1.05it/s]\n 75%|███████▌  | 150/200 [04:56<01:27,  1.75s/it]\n 76%|███████▌  | 151/200 [05:00<01:52,  2.30s/it]\n 76%|███████▌  | 152/200 [05:03<02:09,  2.69s/it]\n 76%|███████▋  | 153/200 [05:07<02:19,  2.96s/it]\n 77%|███████▋  | 154/200 [05:07<01:38,  2.15s/it]\n 78%|███████▊  | 155/200 [05:07<01:11,  1.58s/it]\n 78%|███████▊  | 156/200 [05:08<00:52,  1.19s/it]\n 78%|███████▊  | 157/200 [05:11<01:22,  1.92s/it]\n 79%|███████▉  | 158/200 [05:15<01:41,  2.42s/it]\n 80%|███████▉  | 159/200 [05:15<01:12,  1.77s/it]\n 80%|████████  | 160/200 [05:19<01:32,  2.32s/it]\n 80%|████████  | 161/200 [05:22<01:45,  2.69s/it]\n 81%|████████  | 162/200 [05:22<01:14,  1.96s/it]\n 82%|████████▏ | 163/200 [05:23<00:53,  1.45s/it]\n 82%|████████▏ | 164/200 [05:23<00:39,  1.10s/it]\n 82%|████████▎ | 165/200 [05:27<01:04,  1.85s/it]\n 83%|████████▎ | 166/200 [05:30<01:20,  2.37s/it]\n 84%|████████▎ | 167/200 [05:34<01:30,  2.73s/it]\n 84%|████████▍ | 168/200 [05:37<01:35,  2.99s/it]\n 84%|████████▍ | 169/200 [05:41<01:38,  3.18s/it]\n 85%|████████▌ | 170/200 [05:45<01:39,  3.31s/it]\n 86%|████████▌ | 171/200 [05:48<01:39,  3.45s/it]\n 86%|████████▌ | 172/200 [05:48<01:08,  2.45s/it]\n 86%|████████▋ | 173/200 [05:49<00:48,  1.80s/it]\n 87%|████████▋ | 174/200 [05:52<01:00,  2.33s/it]\n 88%|████████▊ | 175/200 [05:56<01:08,  2.74s/it]\n 88%|████████▊ | 176/200 [06:00<01:13,  3.06s/it]\n 88%|████████▊ | 177/200 [06:03<01:14,  3.22s/it]\n 89%|████████▉ | 178/200 [06:04<00:50,  2.29s/it]\n 90%|████████▉ | 179/200 [06:04<00:35,  1.69s/it]\n 90%|█████████ | 180/200 [06:04<00:25,  1.26s/it]\n 90%|█████████ | 181/200 [06:08<00:37,  1.99s/it]\n 91%|█████████ | 182/200 [06:11<00:44,  2.50s/it]\n 92%|█████████▏| 183/200 [06:12<00:30,  1.82s/it]\n 92%|█████████▏| 184/200 [06:15<00:37,  2.34s/it]\n 92%|█████████▎| 185/200 [06:19<00:40,  2.72s/it]\n 93%|█████████▎| 186/200 [06:23<00:42,  3.02s/it]\n 94%|█████████▎| 187/200 [06:26<00:41,  3.20s/it]\n 94%|█████████▍| 188/200 [06:30<00:39,  3.32s/it]\n 94%|█████████▍| 189/200 [06:33<00:37,  3.39s/it]\n 95%|█████████▌| 190/200 [06:33<00:24,  2.41s/it]\n 96%|█████████▌| 191/200 [06:37<00:25,  2.78s/it]\n 96%|█████████▌| 192/200 [06:41<00:24,  3.07s/it]\n 96%|█████████▋| 193/200 [06:41<00:15,  2.19s/it]\n 97%|█████████▋| 194/200 [06:45<00:15,  2.65s/it]\n 98%|█████████▊| 195/200 [06:48<00:14,  2.95s/it]\n 98%|█████████▊| 196/200 [06:52<00:12,  3.11s/it]\n 98%|█████████▊| 197/200 [06:56<00:09,  3.29s/it]\n 99%|█████████▉| 198/200 [06:59<00:06,  3.38s/it]\n100%|█████████▉| 199/200 [06:59<00:02,  2.40s/it]\n100%|██████████| 200/200 [07:03<00:00,  2.81s/it]\n100%|██████████| 200/200 [07:03<00:00,  2.12s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752856402/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_1752856402/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_1752856402/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_1752856402/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 : 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 (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 : 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 : 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 : 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 : 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 : 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 : 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 : 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 (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 : 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 : 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 : 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): 423.5258102416992\nerrors 89\nmean length: 1.665\n\nthroughput (request / second): 0.47222623784336376\nthroughput (character / second): 0.7862566860092006\naverage request duration (s) 2.1175157380104066\n50%ile request duration (s) 3.5724856853485107\n75%ile request duration (s) 3.6245741844177246\n90%ile request duration (s) 3.716040778160095\n95%ile request duration (s) 3.7407912373542787\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-llama3-200m-v2-t-76584-v4-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-76584-v4-profiler
Service chaiml-llama3-200m-v2-t-76584-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.69s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 5.11s
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 chaiml-llama3-200m-v2-t-76584-v4-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v4-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v4-profiler ready after 101.4569661617279s
Pipeline stage MKMLProfilerDeployer completed in 102.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml:/code/chaiverse_profiler_1752857024 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752857024 && 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_1752857024/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml:/code/chaiverse_profiler_1752857530 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752857530 && 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_1752857530/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml:/code/chaiverse_profiler_1752857981 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplolzqml --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752857981 && 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_1752857981/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<11:39,  3.52s/it]\n  1%|          | 2/200 [00:07<11:49,  3.58s/it]\n  2%|▏         | 3/200 [00:07<06:35,  2.01s/it]\n  2%|▏         | 4/200 [00:07<04:20,  1.33s/it]\n  2%|▎         | 5/200 [00:07<03:06,  1.04it/s]\n  3%|▎         | 6/200 [00:11<06:00,  1.86s/it]\n  4%|▎         | 7/200 [00:15<07:47,  2.42s/it]\n  4%|▍         | 8/200 [00:15<05:36,  1.75s/it]\n  4%|▍         | 9/200 [00:19<07:33,  2.37s/it]\n  5%|▌         | 10/200 [00:19<05:28,  1.73s/it]\n  6%|▌         | 11/200 [00:19<04:03,  1.29s/it]\n  6%|▌         | 12/200 [00:19<03:05,  1.01it/s]\n  6%|▋         | 13/200 [00:23<05:36,  1.80s/it]\n  7%|▋         | 14/200 [00:23<04:11,  1.35s/it]\n  8%|▊         | 15/200 [00:24<03:13,  1.04s/it]\n  8%|▊         | 16/200 [00:24<02:23,  1.28it/s]\n  8%|▊         | 17/200 [00:28<05:19,  1.74s/it]\n  9%|▉         | 18/200 [00:32<07:03,  2.32s/it]\n 10%|▉         | 19/200 [00:35<08:12,  2.72s/it]\n 10%|█         | 20/200 [00:39<09:02,  3.01s/it]\n 10%|█         | 21/200 [00:39<06:24,  2.15s/it]\n 11%|█         | 22/200 [00:39<04:44,  1.60s/it]\n 12%|█▏        | 23/200 [00:40<03:35,  1.22s/it]\n 12%|█▏        | 24/200 [00:44<05:47,  1.98s/it]\n 12%|█▎        | 25/200 [00:47<07:16,  2.49s/it]\n 13%|█▎        | 26/200 [00:48<05:20,  1.84s/it]\n 14%|█▎        | 27/200 [00:48<03:59,  1.38s/it]\n 14%|█▍        | 28/200 [00:51<05:50,  2.04s/it]\n 14%|█▍        | 29/200 [00:52<04:19,  1.52s/it]\n 15%|█▌        | 30/200 [00:55<06:07,  2.16s/it]\n 16%|█▌        | 31/200 [00:56<04:29,  1.59s/it]\n 16%|█▌        | 32/200 [00:56<03:23,  1.21s/it]\n 16%|█▋        | 33/200 [01:00<05:21,  1.92s/it]\n 17%|█▋        | 34/200 [01:03<06:40,  2.41s/it]\n 18%|█▊        | 35/200 [01:03<04:45,  1.73s/it]\n 18%|█▊        | 36/200 [01:07<06:21,  2.33s/it]\n 18%|█▊        | 37/200 [01:07<04:31,  1.67s/it]\n 19%|█▉        | 38/200 [01:11<06:07,  2.27s/it]\n 20%|█▉        | 39/200 [01:11<04:21,  1.63s/it]\n 20%|██        | 40/200 [01:14<05:50,  2.19s/it]\n 20%|██        | 41/200 [01:18<06:57,  2.63s/it]\n 21%|██        | 42/200 [01:22<07:35,  2.88s/it]\n 22%|██▏       | 43/200 [01:25<08:00,  3.06s/it]\n 22%|██▏       | 44/200 [01:25<05:40,  2.18s/it]\n 22%|██▎       | 45/200 [01:29<06:40,  2.58s/it]\n 23%|██▎       | 46/200 [01:32<07:16,  2.83s/it]\n 24%|██▎       | 47/200 [01:36<07:47,  3.06s/it]\n 24%|██▍       | 48/200 [01:39<08:02,  3.17s/it]\n 24%|██▍       | 49/200 [01:39<05:40,  2.26s/it]\n 25%|██▌       | 50/200 [01:39<04:08,  1.66s/it]\n 26%|██▌       | 51/200 [01:43<05:27,  2.20s/it]\n 26%|██▌       | 52/200 [01:43<03:58,  1.61s/it]\n 26%|██▋       | 53/200 [01:43<02:56,  1.20s/it]\n 27%|██▋       | 54/200 [01:44<02:14,  1.09it/s]\n 28%|██▊       | 55/200 [01:44<01:44,  1.39it/s]\n 28%|██▊       | 56/200 [01:47<03:41,  1.54s/it]\n 28%|██▊       | 57/200 [01:48<02:44,  1.15s/it]\n 29%|██▉       | 58/200 [01:51<04:22,  1.85s/it]\n 30%|██▉       | 59/200 [01:51<03:12,  1.37s/it]\n 30%|███       | 60/200 [01:55<04:40,  2.00s/it]\n 30%|███       | 61/200 [01:58<05:41,  2.45s/it]\n 31%|███       | 62/200 [02:02<06:22,  2.77s/it]\n 32%|███▏      | 63/200 [02:02<04:37,  2.02s/it]\n 32%|███▏      | 64/200 [02:02<03:24,  1.50s/it]\n 32%|███▎      | 65/200 [02:03<02:33,  1.14s/it]\n 33%|███▎      | 66/200 [02:06<04:09,  1.86s/it]\n 34%|███▎      | 67/200 [02:06<02:58,  1.34s/it]\n 34%|███▍      | 68/200 [02:07<02:14,  1.02s/it]\n 34%|███▍      | 69/200 [02:10<03:55,  1.80s/it]\n 35%|███▌      | 70/200 [02:14<04:57,  2.29s/it]\n 36%|███▌      | 71/200 [02:17<05:39,  2.63s/it]\n 36%|███▌      | 72/200 [02:17<04:00,  1.88s/it]\n 36%|███▋      | 73/200 [02:18<02:58,  1.40s/it]\n 37%|███▋      | 74/200 [02:21<04:16,  2.03s/it]\n 38%|███▊      | 75/200 [02:21<03:06,  1.49s/it]\n 38%|███▊      | 76/200 [02:25<04:17,  2.08s/it]\n 38%|███▊      | 77/200 [02:28<05:14,  2.56s/it]\n 39%|███▉      | 78/200 [02:29<03:43,  1.83s/it]\n 40%|███▉      | 79/200 [02:32<04:44,  2.35s/it]\n 40%|████      | 80/200 [02:36<05:23,  2.70s/it]\n 40%|████      | 81/200 [02:39<05:49,  2.93s/it]\n 41%|████      | 82/200 [02:39<04:07,  2.10s/it]\n 42%|████▏     | 83/200 [02:43<04:59,  2.56s/it]\n 42%|████▏     | 84/200 [02:43<03:32,  1.83s/it]\n 42%|████▎     | 85/200 [02:47<04:32,  2.37s/it]\n 43%|████▎     | 86/200 [02:47<03:13,  1.70s/it]\n 44%|████▎     | 87/200 [02:50<04:12,  2.23s/it]\n 44%|████▍     | 88/200 [02:54<04:55,  2.63s/it]\n 44%|████▍     | 89/200 [02:54<03:28,  1.88s/it]\n 45%|████▌     | 90/200 [02:57<04:19,  2.36s/it]\n 46%|████▌     | 91/200 [02:58<03:07,  1.72s/it]\n 46%|████▌     | 92/200 [03:01<04:01,  2.24s/it]\n 46%|████▋     | 93/200 [03:05<04:45,  2.67s/it]\n 47%|████▋     | 94/200 [03:05<03:22,  1.91s/it]\n 48%|████▊     | 95/200 [03:08<04:11,  2.40s/it]\n 48%|████▊     | 96/200 [03:12<04:44,  2.73s/it]\n 48%|████▊     | 97/200 [03:15<05:06,  2.97s/it]\n 49%|████▉     | 98/200 [03:19<05:18,  3.12s/it]\n 50%|████▉     | 99/200 [03:19<03:44,  2.22s/it]\n 50%|█████     | 100/200 [03:23<04:23,  2.64s/it]\n 50%|█████     | 101/200 [03:23<03:11,  1.93s/it]\n 51%|█████     | 102/200 [03:27<04:03,  2.49s/it]\n 52%|█████▏    | 103/200 [03:30<04:37,  2.86s/it]\n 52%|█████▏    | 104/200 [03:31<03:19,  2.08s/it]\n 52%|█████▎    | 105/200 [03:31<02:26,  1.55s/it]\n 53%|█████▎    | 106/200 [03:31<01:49,  1.17s/it]\n 54%|█████▎    | 107/200 [03:32<01:24,  1.11it/s]\n 54%|█████▍    | 108/200 [03:35<02:43,  1.77s/it]\n 55%|█████▍    | 109/200 [03:39<03:40,  2.42s/it]\n 55%|█████▌    | 110/200 [03:40<02:40,  1.79s/it]\n 56%|█████▌    | 111/200 [03:43<03:32,  2.39s/it]\n 56%|█████▌    | 112/200 [03:44<02:35,  1.77s/it]\n 56%|█████▋    | 113/200 [03:44<01:55,  1.33s/it]\n 57%|█████▋    | 114/200 [03:48<03:02,  2.12s/it]\n 57%|█████▊    | 115/200 [03:48<02:14,  1.59s/it]\n 58%|█████▊    | 116/200 [03:49<01:36,  1.15s/it]\n 58%|█████▊    | 117/200 [03:52<02:45,  2.00s/it]\n 59%|█████▉    | 118/200 [03:56<03:25,  2.50s/it]\n 60%|█████▉    | 119/200 [03:56<02:29,  1.85s/it]\n 60%|██████    | 120/200 [03:57<01:50,  1.38s/it]\n 60%|██████    | 121/200 [04:01<02:46,  2.10s/it]\n 61%|██████    | 122/200 [04:01<02:02,  1.57s/it]\n 62%|██████▏   | 123/200 [04:01<01:31,  1.19s/it]\n 62%|██████▏   | 124/200 [04:05<02:29,  1.97s/it]\n 62%|██████▎   | 125/200 [04:09<03:09,  2.52s/it]\n 63%|██████▎   | 126/200 [04:09<02:16,  1.84s/it]\n 64%|██████▎   | 127/200 [04:09<01:41,  1.38s/it]\n 64%|██████▍   | 128/200 [04:10<01:16,  1.07s/it]\n 64%|██████▍   | 129/200 [04:10<00:59,  1.20it/s]\n 65%|██████▌   | 130/200 [04:10<00:47,  1.46it/s]\n 66%|██████▌   | 131/200 [04:14<01:51,  1.62s/it]\n 66%|██████▌   | 132/200 [04:18<02:35,  2.28s/it]\n 66%|██████▋   | 133/200 [04:22<03:02,  2.73s/it]\n 67%|██████▋   | 134/200 [04:22<02:08,  1.95s/it]\n 68%|██████▊   | 135/200 [04:26<02:44,  2.53s/it]\n 68%|██████▊   | 136/200 [04:30<03:10,  2.98s/it]\n 68%|██████▊   | 137/200 [04:34<03:27,  3.29s/it]\n 69%|██████▉   | 138/200 [04:34<02:25,  2.35s/it]\n 70%|██████▉   | 139/200 [04:38<02:50,  2.79s/it]\n 70%|███████   | 140/200 [04:42<03:08,  3.14s/it]\n 70%|███████   | 141/200 [04:46<03:17,  3.35s/it]\n 71%|███████   | 142/200 [04:49<03:21,  3.48s/it]\n 72%|███████▏  | 143/200 [04:49<02:21,  2.48s/it]\n 72%|███████▏  | 144/200 [04:53<02:44,  2.93s/it]\n 72%|███████▎  | 145/200 [04:57<02:54,  3.18s/it]\n 73%|███████▎  | 146/200 [05:01<03:02,  3.38s/it]\n 74%|███████▎  | 147/200 [05:05<03:05,  3.49s/it]\n 74%|███████▍  | 148/200 [05:09<03:08,  3.62s/it]\n 74%|███████▍  | 149/200 [05:13<03:08,  3.70s/it]\n 75%|███████▌  | 150/200 [05:16<03:06,  3.73s/it]\n 76%|███████▌  | 151/200 [05:20<03:05,  3.78s/it]\n 76%|███████▌  | 152/200 [05:24<02:59,  3.75s/it]\n 76%|███████▋  | 153/200 [05:28<02:59,  3.82s/it]\n 77%|███████▋  | 154/200 [05:32<02:54,  3.80s/it]\n 78%|███████▊  | 155/200 [05:36<02:52,  3.83s/it]\n 78%|███████▊  | 156/200 [05:39<02:48,  3.83s/it]\n 78%|███████▊  | 157/200 [05:43<02:43,  3.81s/it]\n 79%|███████▉  | 158/200 [05:43<01:53,  2.71s/it]\n 80%|███████▉  | 159/200 [05:47<02:05,  3.06s/it]\n 80%|████████  | 160/200 [05:51<02:12,  3.30s/it]\n 80%|████████  | 161/200 [05:51<01:31,  2.36s/it]\n 81%|████████  | 162/200 [05:55<01:47,  2.82s/it]\n 82%|████████▏ | 163/200 [05:59<01:56,  3.15s/it]\n 82%|████████▏ | 164/200 [06:03<02:01,  3.36s/it]\n 82%|████████▎ | 165/200 [06:07<02:02,  3.50s/it]\n 83%|████████▎ | 166/200 [06:11<02:03,  3.62s/it]\n 84%|████████▎ | 167/200 [06:11<01:25,  2.58s/it]\n 84%|████████▍ | 168/200 [06:15<01:34,  2.94s/it]\n 84%|████████▍ | 169/200 [06:15<01:07,  2.17s/it]\n 85%|████████▌ | 170/200 [06:15<00:48,  1.62s/it]\n 86%|████████▌ | 171/200 [06:19<01:05,  2.27s/it]\n 86%|████████▌ | 172/200 [06:23<01:17,  2.76s/it]\n 86%|████████▋ | 173/200 [06:27<01:24,  3.14s/it]\n 87%|████████▋ | 174/200 [06:31<01:26,  3.31s/it]\n 88%|████████▊ | 175/200 [06:34<01:26,  3.45s/it]\n 88%|████████▊ | 176/200 [06:38<01:26,  3.59s/it]\n 88%|████████▊ | 177/200 [06:42<01:24,  3.65s/it]\n 89%|████████▉ | 178/200 [06:46<01:21,  3.72s/it]\n 90%|████████▉ | 179/200 [06:50<01:18,  3.75s/it]\n 90%|█████████ | 180/200 [06:54<01:15,  3.78s/it]\n 90%|█████████ | 181/200 [06:54<00:51,  2.69s/it]\n 91%|█████████ | 182/200 [06:54<00:36,  2.01s/it]\n 92%|█████████▏| 183/200 [06:55<00:25,  1.50s/it]\n 92%|█████████▏| 184/200 [06:58<00:35,  2.21s/it]\n 92%|█████████▎| 185/200 [06:59<00:24,  1.65s/it]\n 93%|█████████▎| 186/200 [07:03<00:32,  2.31s/it]\n 94%|█████████▎| 187/200 [07:03<00:22,  1.71s/it]\n 94%|█████████▍| 188/200 [07:07<00:28,  2.34s/it]\n 94%|█████████▍| 189/200 [07:07<00:19,  1.75s/it]\n 95%|█████████▌| 190/200 [07:11<00:23,  2.38s/it]\n 96%|█████████▌| 191/200 [07:15<00:25,  2.83s/it]\n 96%|█████████▌| 192/200 [07:19<00:25,  3.14s/it]\n 96%|█████████▋| 193/200 [07:19<00:16,  2.30s/it]\n 97%|█████████▋| 194/200 [07:19<00:09,  1.65s/it]\n 98%|█████████▊| 195/200 [07:20<00:06,  1.25s/it]\n 98%|█████████▊| 196/200 [07:23<00:07,  2.00s/it]\n 98%|█████████▊| 197/200 [07:24<00:04,  1.49s/it]\n 99%|█████████▉| 198/200 [07:24<00:02,  1.13s/it]\n100%|█████████▉| 199/200 [07:24<00:00,  1.14it/s]\n100%|██████████| 200/200 [07:28<00:00,  1.78s/it]\n100%|██████████| 200/200 [07:28<00:00,  2.24s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752857981/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_1752857981/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_1752857981/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_1752857981/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 : 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 (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 : 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 (1,)"}\')\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 (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 : 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 (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 : 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 (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 : 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 : 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 : 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 : 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 (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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 448.57846665382385\nerrors 85\nmean length: 1.725\n\nthroughput (request / second): 0.44585287718312083\nthroughput (character / second): 0.7690962131408835\naverage request duration (s) 2.2427301037311556\n50%ile request duration (s) 3.4845131635665894\n75%ile request duration (s) 3.780166983604431\n90%ile request duration (s) 3.883425712585449\n95%ile request duration (s) 3.9286841869354245\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-llama3-200m-v2-t-76584-v4-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-76584-v4-profiler
Service chaiml-llama3-200m-v2-t-76584-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.59s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 4.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v4-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v4-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v4-profiler ready after 313.1949882507324s
Pipeline stage MKMLProfilerDeployer completed in 313.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6:/code/chaiverse_profiler_1752858828 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752858828 && 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_1752858828/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6:/code/chaiverse_profiler_1752859238 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752859238 && 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_1752859238/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6:/code/chaiverse_profiler_1752859621 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v3039747b3f4e4db19649979ab0e52782-deplobg5l6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752859621 && 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_1752859621/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<11:04,  3.34s/it]\n  1%|          | 2/200 [00:03<04:58,  1.51s/it]\n  2%|▏         | 3/200 [00:06<07:47,  2.37s/it]\n  2%|▏         | 4/200 [00:10<09:03,  2.78s/it]\n  2%|▎         | 5/200 [00:10<06:01,  1.86s/it]\n  3%|▎         | 6/200 [00:13<07:42,  2.38s/it]\n  4%|▎         | 7/200 [00:17<08:50,  2.75s/it]\n  4%|▍         | 8/200 [00:20<09:28,  2.96s/it]\n  4%|▍         | 9/200 [00:21<06:35,  2.07s/it]\n  5%|▌         | 10/200 [00:24<07:50,  2.48s/it]\n  6%|▌         | 11/200 [00:27<08:46,  2.79s/it]\n  6%|▌         | 12/200 [00:28<06:11,  1.97s/it]\n  6%|▋         | 13/200 [00:28<04:31,  1.45s/it]\n  7%|▋         | 14/200 [00:28<03:23,  1.09s/it]\n  8%|▊         | 15/200 [00:28<02:35,  1.19it/s]\n  8%|▊         | 16/200 [00:32<04:57,  1.62s/it]\n  8%|▊         | 17/200 [00:35<06:33,  2.15s/it]\n  9%|▉         | 18/200 [00:38<07:39,  2.52s/it]\n 10%|▉         | 19/200 [00:42<08:23,  2.78s/it]\n 10%|█         | 20/200 [00:45<08:53,  2.97s/it]\n 10%|█         | 21/200 [00:49<09:13,  3.09s/it]\n 11%|█         | 22/200 [00:49<06:37,  2.23s/it]\n 12%|█▏        | 23/200 [00:52<07:37,  2.58s/it]\n 12%|█▏        | 24/200 [00:53<05:30,  1.88s/it]\n 12%|█▎        | 25/200 [00:56<06:48,  2.34s/it]\n 13%|█▎        | 26/200 [00:56<04:56,  1.70s/it]\n 14%|█▎        | 27/200 [01:00<06:26,  2.23s/it]\n 14%|█▍        | 28/200 [01:00<04:41,  1.64s/it]\n 14%|█▍        | 29/200 [01:00<03:28,  1.22s/it]\n 15%|█▌        | 30/200 [01:04<05:18,  1.87s/it]\n 16%|█▌        | 31/200 [01:07<06:33,  2.33s/it]\n 16%|█▌        | 32/200 [01:07<04:39,  1.67s/it]\n 16%|█▋        | 33/200 [01:10<06:03,  2.18s/it]\n 17%|█▋        | 34/200 [01:11<04:24,  1.59s/it]\n 18%|█▊        | 35/200 [01:14<05:59,  2.18s/it]\n 18%|█▊        | 36/200 [01:18<06:56,  2.54s/it]\n 18%|█▊        | 37/200 [01:21<07:36,  2.80s/it]\n 19%|█▉        | 38/200 [01:24<08:02,  2.98s/it]\n 20%|█▉        | 39/200 [01:24<05:41,  2.12s/it]\n 20%|██        | 40/200 [01:25<04:08,  1.55s/it]\n 20%|██        | 41/200 [01:28<05:41,  2.15s/it]\n 21%|██        | 42/200 [01:28<04:03,  1.54s/it]\n 22%|██▏       | 43/200 [01:29<03:01,  1.15s/it]\n 22%|██▏       | 44/200 [01:32<04:45,  1.83s/it]\n 22%|██▎       | 45/200 [01:35<06:00,  2.33s/it]\n 23%|██▎       | 46/200 [01:36<04:16,  1.66s/it]\n 24%|██▎       | 47/200 [01:36<03:09,  1.24s/it]\n 24%|██▍       | 48/200 [01:36<02:23,  1.06it/s]\n 24%|██▍       | 49/200 [01:40<04:13,  1.68s/it]\n 25%|██▌       | 50/200 [01:40<03:05,  1.24s/it]\n 26%|██▌       | 51/200 [01:43<04:42,  1.89s/it]\n 26%|██▌       | 52/200 [01:47<05:51,  2.37s/it]\n 26%|██▋       | 53/200 [01:47<04:09,  1.70s/it]\n 27%|██▋       | 54/200 [01:50<05:26,  2.24s/it]\n 28%|██▊       | 55/200 [01:54<06:14,  2.58s/it]\n 28%|██▊       | 56/200 [01:57<06:40,  2.78s/it]\n 28%|██▊       | 57/200 [02:00<07:09,  3.00s/it]\n 29%|██▉       | 58/200 [02:04<07:22,  3.12s/it]\n 30%|██▉       | 59/200 [02:04<05:12,  2.22s/it]\n 30%|███       | 60/200 [02:04<03:47,  1.63s/it]\n 30%|███       | 61/200 [02:04<02:48,  1.22s/it]\n 31%|███       | 62/200 [02:05<02:07,  1.08it/s]\n 32%|███▏      | 63/200 [02:05<01:38,  1.38it/s]\n 32%|███▏      | 64/200 [02:05<01:19,  1.71it/s]\n 32%|███▎      | 65/200 [02:05<01:05,  2.06it/s]\n 33%|███▎      | 66/200 [02:06<00:56,  2.39it/s]\n 34%|███▎      | 67/200 [02:09<02:55,  1.32s/it]\n 34%|███▍      | 68/200 [02:09<02:07,  1.04it/s]\n 34%|███▍      | 69/200 [02:10<01:38,  1.33it/s]\n 35%|███▌      | 70/200 [02:13<03:21,  1.55s/it]\n 36%|███▌      | 71/200 [02:16<04:30,  2.10s/it]\n 36%|███▌      | 72/200 [02:20<05:23,  2.52s/it]\n 36%|███▋      | 73/200 [02:20<03:48,  1.80s/it]\n 37%|███▋      | 74/200 [02:20<02:48,  1.34s/it]\n 38%|███▊      | 75/200 [02:24<04:05,  1.96s/it]\n 38%|███▊      | 76/200 [02:24<02:59,  1.45s/it]\n 38%|███▊      | 77/200 [02:27<04:12,  2.05s/it]\n 39%|███▉      | 78/200 [02:31<04:57,  2.44s/it]\n 40%|███▉      | 79/200 [02:34<05:29,  2.72s/it]\n 40%|████      | 80/200 [02:34<03:57,  1.98s/it]\n 40%|████      | 81/200 [02:35<02:53,  1.46s/it]\n 41%|████      | 82/200 [02:38<04:01,  2.05s/it]\n 42%|████▏     | 83/200 [02:38<02:55,  1.50s/it]\n 42%|████▏     | 84/200 [02:38<02:10,  1.13s/it]\n 42%|████▎     | 85/200 [02:39<01:39,  1.16it/s]\n 43%|████▎     | 86/200 [02:42<03:06,  1.63s/it]\n 44%|████▎     | 87/200 [02:42<02:17,  1.22s/it]\n 44%|████▍     | 88/200 [02:43<01:43,  1.08it/s]\n 44%|████▍     | 89/200 [02:43<01:21,  1.37it/s]\n 45%|████▌     | 90/200 [02:46<02:49,  1.54s/it]\n 46%|████▌     | 91/200 [02:50<03:48,  2.10s/it]\n 46%|████▌     | 92/200 [02:53<04:25,  2.46s/it]\n 46%|████▋     | 93/200 [02:57<04:59,  2.80s/it]\n 47%|████▋     | 94/200 [02:57<03:31,  2.00s/it]\n 48%|████▊     | 95/200 [03:00<04:12,  2.41s/it]\n 48%|████▊     | 96/200 [03:00<03:02,  1.75s/it]\n 48%|████▊     | 97/200 [03:04<03:52,  2.25s/it]\n 49%|████▉     | 98/200 [03:07<04:28,  2.63s/it]\n 50%|████▉     | 99/200 [03:11<04:45,  2.83s/it]\n 50%|█████     | 100/200 [03:11<03:25,  2.06s/it]\n 50%|█████     | 101/200 [03:11<02:30,  1.52s/it]\n 51%|█████     | 102/200 [03:11<01:51,  1.14s/it]\n 52%|█████▏    | 103/200 [03:15<02:56,  1.82s/it]\n 52%|█████▏    | 104/200 [03:18<03:40,  2.30s/it]\n 52%|█████▎    | 105/200 [03:18<02:39,  1.68s/it]\n 53%|█████▎    | 106/200 [03:22<03:25,  2.19s/it]\n 54%|█████▎    | 107/200 [03:25<03:56,  2.54s/it]\n 54%|█████▍    | 108/200 [03:29<04:20,  2.83s/it]\n 55%|█████▍    | 109/200 [03:32<04:32,  3.00s/it]\n 55%|█████▌    | 110/200 [03:35<04:40,  3.12s/it]\n 56%|█████▌    | 111/200 [03:36<03:17,  2.22s/it]\n 56%|█████▌    | 112/200 [03:36<02:23,  1.63s/it]\n 56%|█████▋    | 113/200 [03:36<01:45,  1.21s/it]\n 57%|█████▋    | 114/200 [03:39<02:42,  1.89s/it]\n 57%|█████▊    | 115/200 [03:40<01:58,  1.39s/it]\n 58%|█████▊    | 116/200 [03:40<01:27,  1.04s/it]\n 58%|█████▊    | 117/200 [03:43<02:24,  1.74s/it]\n 59%|█████▉    | 118/200 [03:44<01:45,  1.28s/it]\n 60%|█████▉    | 119/200 [03:44<01:18,  1.03it/s]\n 60%|██████    | 120/200 [03:47<02:18,  1.73s/it]\n 60%|██████    | 121/200 [03:47<01:41,  1.28s/it]\n 61%|██████    | 122/200 [03:51<02:28,  1.90s/it]\n 62%|██████▏   | 123/200 [03:54<03:02,  2.37s/it]\n 62%|██████▏   | 124/200 [03:54<02:09,  1.70s/it]\n 62%|██████▎   | 125/200 [03:58<02:46,  2.22s/it]\n 63%|██████▎   | 126/200 [04:01<03:10,  2.57s/it]\n 64%|██████▎   | 127/200 [04:05<03:25,  2.82s/it]\n 64%|██████▍   | 128/200 [04:08<03:35,  2.99s/it]\n 64%|██████▍   | 129/200 [04:11<03:41,  3.12s/it]\n 65%|██████▌   | 130/200 [04:12<02:35,  2.22s/it]\n 66%|██████▌   | 131/200 [04:15<02:57,  2.58s/it]\n 66%|██████▌   | 132/200 [04:19<03:14,  2.86s/it]\n 66%|██████▋   | 133/200 [04:22<03:22,  3.02s/it]\n 67%|██████▋   | 134/200 [04:25<03:27,  3.14s/it]\n 68%|██████▊   | 135/200 [04:25<02:25,  2.23s/it]\n 68%|██████▊   | 136/200 [04:29<02:45,  2.58s/it]\n 68%|██████▊   | 137/200 [04:32<03:02,  2.89s/it]\n 69%|██████▉   | 138/200 [04:33<02:07,  2.06s/it]\n 70%|██████▉   | 139/200 [04:36<02:29,  2.45s/it]\n 70%|███████   | 140/200 [04:36<01:47,  1.79s/it]\n 70%|███████   | 141/200 [04:36<01:18,  1.32s/it]\n 71%|███████   | 142/200 [04:40<01:53,  1.95s/it]\n 72%|███████▏  | 143/200 [04:40<01:22,  1.44s/it]\n 72%|███████▏  | 144/200 [04:40<01:00,  1.09s/it]\n 72%|███████▎  | 145/200 [04:44<01:38,  1.78s/it]\n 73%|███████▎  | 146/200 [04:44<01:11,  1.32s/it]\n 74%|███████▎  | 147/200 [04:47<01:42,  1.94s/it]\n 74%|███████▍  | 148/200 [04:51<02:04,  2.40s/it]\n 74%|███████▍  | 149/200 [04:54<02:18,  2.71s/it]\n 75%|███████▌  | 150/200 [04:55<01:38,  1.98s/it]\n 76%|███████▌  | 151/200 [04:55<01:11,  1.46s/it]\n 76%|███████▌  | 152/200 [04:58<01:38,  2.05s/it]\n 76%|███████▋  | 153/200 [04:59<01:11,  1.52s/it]\n 77%|███████▋  | 154/200 [05:02<01:35,  2.09s/it]\n 78%|███████▊  | 155/200 [05:05<01:51,  2.47s/it]\n 78%|███████▊  | 156/200 [05:06<01:19,  1.80s/it]\n 78%|███████▊  | 157/200 [05:06<00:57,  1.34s/it]\n 79%|███████▉  | 158/200 [05:09<01:22,  1.96s/it]\n 80%|███████▉  | 159/200 [05:13<01:38,  2.40s/it]\n 80%|████████  | 160/200 [05:16<01:48,  2.72s/it]\n 80%|████████  | 161/200 [05:20<01:54,  2.95s/it]\n 81%|████████  | 162/200 [05:23<01:57,  3.10s/it]\n 82%|████████▏ | 163/200 [05:23<01:21,  2.20s/it]\n 82%|████████▏ | 164/200 [05:23<00:58,  1.62s/it]\n 82%|████████▎ | 165/200 [05:24<00:42,  1.21s/it]\n 83%|████████▎ | 166/200 [05:24<00:31,  1.08it/s]\n 84%|████████▎ | 167/200 [05:27<00:55,  1.67s/it]\n 84%|████████▍ | 168/200 [05:28<00:39,  1.24s/it]\n 84%|████████▍ | 169/200 [05:31<00:58,  1.90s/it]\n 85%|████████▌ | 170/200 [05:34<01:10,  2.34s/it]\n 86%|████████▌ | 171/200 [05:35<00:49,  1.72s/it]\n 86%|████████▌ | 172/200 [05:38<01:02,  2.23s/it]\n 86%|████████▋ | 173/200 [05:42<01:10,  2.61s/it]\n 87%|████████▋ | 174/200 [05:45<01:13,  2.84s/it]\n 88%|████████▊ | 175/200 [05:45<00:50,  2.03s/it]\n 88%|████████▊ | 176/200 [05:49<00:59,  2.47s/it]\n 88%|████████▊ | 177/200 [05:49<00:41,  1.80s/it]\n 89%|████████▉ | 178/200 [05:49<00:29,  1.34s/it]\n 90%|████████▉ | 179/200 [05:52<00:40,  1.94s/it]\n 90%|█████████ | 180/200 [05:53<00:28,  1.43s/it]\n 90%|█████████ | 181/200 [05:56<00:39,  2.07s/it]\n 91%|█████████ | 182/200 [06:00<00:44,  2.48s/it]\n 92%|█████████▏| 183/200 [06:03<00:46,  2.76s/it]\n 92%|█████████▏| 184/200 [06:03<00:31,  1.96s/it]\n 92%|█████████▎| 185/200 [06:07<00:36,  2.44s/it]\n 93%|█████████▎| 186/200 [06:07<00:24,  1.75s/it]\n 94%|█████████▎| 187/200 [06:10<00:29,  2.25s/it]\n 94%|█████████▍| 188/200 [06:14<00:31,  2.63s/it]\n 94%|█████████▍| 189/200 [06:14<00:20,  1.88s/it]\n 95%|█████████▌| 190/200 [06:18<00:24,  2.41s/it]\n 96%|█████████▌| 191/200 [06:18<00:15,  1.72s/it]\n 96%|█████████▌| 192/200 [06:21<00:18,  2.26s/it]\n 96%|█████████▋| 193/200 [06:21<00:11,  1.61s/it]\n 97%|█████████▋| 194/200 [06:25<00:13,  2.19s/it]\n 98%|█████████▊| 195/200 [06:28<00:12,  2.55s/it]\n 98%|█████████▊| 196/200 [06:28<00:07,  1.82s/it]\n 98%|█████████▊| 197/200 [06:29<00:04,  1.35s/it]\n 99%|█████████▉| 198/200 [06:29<00:02,  1.02s/it]\n100%|█████████▉| 199/200 [06:29<00:00,  1.28it/s]\n100%|██████████| 200/200 [06:32<00:00,  1.57s/it]\n100%|██████████| 200/200 [06:32<00:00,  1.96s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752859621/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_1752859621/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_1752859621/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_1752859621/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 (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 : 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 : 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 (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 : 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 : 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 : 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 (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 : 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 : 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 : 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 : 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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 392.95582270622253\nerrors 91\nmean length: 1.635\n\nthroughput (request / second): 0.5089630651675618\nthroughput (character / second): 0.8321546115489635\naverage request duration (s) 1.9646626257896422\n50%ile request duration (s) 3.3673081398010254\n75%ile request duration (s) 3.4161278009414673\n90%ile request duration (s) 3.4895443439483644\n95%ile request duration (s) 3.5218409419059755\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-llama3-200m-v2-t-76584-v4-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-76584-v4-profiler
Service chaiml-llama3-200m-v2-t-76584-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.79s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama3-200m-v2-t_76584_v4 status is now torndown due to DeploymentManager action
chaiml-llama3-200m-v2-t_76584_v4 status is now torndown due to DeploymentManager action