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-89339-v1-mkmlizer
Waiting for job on chaiml-llama3-200m-v2-t-89339-v1-mkmlizer to finish
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ║                                                                     ║
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: Downloaded to shared memory in 27.713s
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: Checking if ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-09e-575 already exists in ChaiML
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp6j7tfgth, device:0
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: quantized model in 20.979s
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: Processed model ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-09e-575 in 48.693s
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia/special_tokens_map.json
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia/config.json
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia/tokenizer_config.json
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia/tokenizer.json
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-89339-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama3-200m-v2-t-89339-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 36.17it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.45it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 48.06it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 41.58it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 47.37it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.81it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 44.01it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 50.25it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 48.22it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:04, 48.28it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 53.06it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.75it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 47.86it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 34.66it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:05, 35.54it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 40.91it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 41.68it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 42.50it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 48.56it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 46.81it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 44.32it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 47.96it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:03, 45.19it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 46.03it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 42.91it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 40.06it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:03, 43.19it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:03, 42.21it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:03, 40.79it/s]
Loading 0:  59%|█████▉    | 171/291 [00:03<00:02, 41.18it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 43.32it/s]
Loading 0:  62%|██████▏   | 181/291 [00:04<00:03, 35.17it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 26.82it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 28.17it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 28.97it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 35.12it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 35.75it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:01, 40.74it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 40.48it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 38.70it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 43.40it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 41.23it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 39.83it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 40.26it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 34.23it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 41.71it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 41.78it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 43.58it/s]
Loading 0:  93%|█████████▎| 270/291 [00:06<00:00, 44.82it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 37.59it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 42.19it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 36.17it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 26.17it/s]
                                                            
Job chaiml-llama3-200m-v2-t-89339-v1-mkmlizer completed after 74.69s with status: succeeded
Stopping job with name chaiml-llama3-200m-v2-t-89339-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama3-200m-v2-t-89339-v1
Waiting for inference service chaiml-llama3-200m-v2-t-89339-v1 to be ready
Inference service chaiml-llama3-200m-v2-t-89339-v1 ready after 201.2033007144928s
Pipeline stage MKMLDeployer completed in 201.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.211731433868408s
Received healthy response to inference request in 5.2121968269348145s
Received healthy response to inference request in 2.445047616958618s
Received healthy response to inference request in 3.611051321029663s
Received healthy response to inference request in 6.676177501678467s
5 requests
0 failed requests
5th percentile: 2.598384380340576
10th percentile: 2.751721143722534
20th percentile: 3.05839467048645
30th percentile: 3.2915954113006594
40th percentile: 3.451323366165161
50th percentile: 3.611051321029663
60th percentile: 4.251509523391723
70th percentile: 4.8919677257537835
80th percentile: 5.504992961883545
90th percentile: 6.090585231781006
95th percentile: 6.383381366729736
99th percentile: 6.617618274688721
mean time: 4.231240940093994
Pipeline stage StressChecker completed in 22.88s
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 0.70s
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 0.71s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_89339_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 0.10s
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-89339-v1-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-89339-v1-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-89339-v1-profiler ready after 202.1011824607849s
Pipeline stage MKMLProfilerDeployer completed in 202.94s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8:/code/chaiverse_profiler_1752021645 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752021645 && 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_1752021645/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8:/code/chaiverse_profiler_1752022094 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752022094 && 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_1752022094/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8:/code/chaiverse_profiler_1752022542 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplod9gm8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752022542 && 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_1752022542/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<00:26,  7.50it/s]\n  1%|          | 2/200 [00:00<00:41,  4.77it/s]\n  2%|▏         | 3/200 [00:03<05:24,  1.64s/it]\n  2%|▏         | 4/200 [00:07<07:49,  2.39s/it]\n  2%|▎         | 5/200 [00:10<08:53,  2.73s/it]\n  3%|▎         | 6/200 [00:10<05:58,  1.85s/it]\n  4%|▎         | 7/200 [00:11<04:16,  1.33s/it]\n  4%|▍         | 8/200 [00:11<03:10,  1.01it/s]\n  4%|▍         | 9/200 [00:14<05:35,  1.75s/it]\n  5%|▌         | 10/200 [00:18<07:11,  2.27s/it]\n  6%|▌         | 11/200 [00:21<08:14,  2.62s/it]\n  6%|▌         | 12/200 [00:21<05:56,  1.90s/it]\n  6%|▋         | 13/200 [00:25<07:21,  2.36s/it]\n  7%|▋         | 14/200 [00:28<08:16,  2.67s/it]\n  8%|▊         | 15/200 [00:28<05:58,  1.94s/it]\n  8%|▊         | 16/200 [00:29<04:24,  1.43s/it]\n  8%|▊         | 17/200 [00:32<06:10,  2.02s/it]\n  9%|▉         | 18/200 [00:32<04:31,  1.49s/it]\n 10%|▉         | 19/200 [00:36<06:16,  2.08s/it]\n 10%|█         | 20/200 [00:39<07:30,  2.50s/it]\n 10%|█         | 21/200 [00:43<08:16,  2.77s/it]\n 11%|█         | 22/200 [00:46<08:46,  2.96s/it]\n 12%|█▏        | 23/200 [00:49<09:09,  3.10s/it]\n 12%|█▏        | 24/200 [00:53<09:20,  3.19s/it]\n 12%|█▎        | 25/200 [00:56<09:29,  3.25s/it]\n 13%|█▎        | 26/200 [00:56<06:42,  2.31s/it]\n 14%|█▎        | 27/200 [01:00<07:40,  2.66s/it]\n 14%|█▍        | 28/200 [01:03<08:13,  2.87s/it]\n 14%|█▍        | 29/200 [01:07<08:43,  3.06s/it]\n 15%|█▌        | 30/200 [01:07<06:10,  2.18s/it]\n 16%|█▌        | 31/200 [01:10<07:10,  2.55s/it]\n 16%|█▌        | 32/200 [01:14<07:55,  2.83s/it]\n 16%|█▋        | 33/200 [01:17<08:20,  3.00s/it]\n 17%|█▋        | 34/200 [01:20<08:37,  3.12s/it]\n 18%|█▊        | 35/200 [01:24<08:42,  3.17s/it]\n 18%|█▊        | 36/200 [01:24<06:15,  2.29s/it]\n 18%|█▊        | 37/200 [01:28<07:16,  2.68s/it]\n 19%|█▉        | 38/200 [01:31<07:47,  2.89s/it]\n 20%|█▉        | 39/200 [01:31<05:30,  2.06s/it]\n 20%|██        | 40/200 [01:35<06:40,  2.50s/it]\n 20%|██        | 41/200 [01:38<07:21,  2.78s/it]\n 21%|██        | 42/200 [01:41<07:46,  2.95s/it]\n 22%|██▏       | 43/200 [01:42<05:30,  2.10s/it]\n 22%|██▏       | 44/200 [01:42<04:01,  1.55s/it]\n 22%|██▎       | 45/200 [01:45<05:31,  2.14s/it]\n 23%|██▎       | 46/200 [01:46<04:01,  1.57s/it]\n 24%|██▎       | 47/200 [01:46<03:00,  1.18s/it]\n 24%|██▍       | 48/200 [01:49<04:40,  1.85s/it]\n 24%|██▍       | 49/200 [01:49<03:27,  1.37s/it]\n 25%|██▌       | 50/200 [01:53<04:59,  2.00s/it]\n 26%|██▌       | 51/200 [01:56<06:03,  2.44s/it]\n 26%|██▌       | 52/200 [02:00<06:42,  2.72s/it]\n 26%|██▋       | 53/200 [02:00<04:51,  1.98s/it]\n 27%|██▋       | 54/200 [02:03<05:51,  2.41s/it]\n 28%|██▊       | 55/200 [02:04<04:15,  1.76s/it]\n 28%|██▊       | 56/200 [02:04<03:09,  1.32s/it]\n 28%|██▊       | 57/200 [02:04<02:23,  1.01s/it]\n 29%|██▉       | 58/200 [02:05<01:52,  1.27it/s]\n 30%|██▉       | 59/200 [02:05<01:23,  1.70it/s]\n 30%|███       | 60/200 [02:08<03:25,  1.47s/it]\n 30%|███       | 61/200 [02:12<04:47,  2.06s/it]\n 31%|███       | 62/200 [02:15<05:38,  2.45s/it]\n 32%|███▏      | 63/200 [02:18<06:13,  2.73s/it]\n 32%|███▏      | 64/200 [02:18<04:24,  1.95s/it]\n 32%|███▎      | 65/200 [02:19<03:14,  1.44s/it]\n 33%|███▎      | 66/200 [02:22<04:36,  2.06s/it]\n 34%|███▎      | 67/200 [02:22<03:17,  1.48s/it]\n 34%|███▍      | 68/200 [02:26<04:38,  2.11s/it]\n 34%|███▍      | 69/200 [02:26<03:18,  1.52s/it]\n 35%|███▌      | 70/200 [02:30<04:34,  2.11s/it]\n 36%|███▌      | 71/200 [02:33<05:21,  2.50s/it]\n 36%|███▌      | 72/200 [02:33<03:48,  1.79s/it]\n 36%|███▋      | 73/200 [02:37<04:47,  2.26s/it]\n 37%|███▋      | 74/200 [02:40<05:27,  2.60s/it]\n 38%|███▊      | 75/200 [02:40<03:56,  1.89s/it]\n 38%|███▊      | 76/200 [02:40<02:53,  1.40s/it]\n 38%|███▊      | 77/200 [02:44<04:10,  2.03s/it]\n 39%|███▉      | 78/200 [02:44<03:02,  1.49s/it]\n 40%|███▉      | 79/200 [02:44<02:16,  1.13s/it]\n 40%|████      | 80/200 [02:48<03:35,  1.80s/it]\n 40%|████      | 81/200 [02:51<04:29,  2.26s/it]\n 41%|████      | 82/200 [02:55<05:07,  2.60s/it]\n 42%|████▏     | 83/200 [02:58<05:38,  2.89s/it]\n 42%|████▏     | 84/200 [02:58<03:58,  2.06s/it]\n 42%|████▎     | 85/200 [03:02<04:46,  2.49s/it]\n 43%|████▎     | 86/200 [03:02<03:22,  1.78s/it]\n 44%|████▎     | 87/200 [03:05<04:20,  2.31s/it]\n 44%|████▍     | 88/200 [03:09<04:54,  2.63s/it]\n 44%|████▍     | 89/200 [03:12<05:16,  2.85s/it]\n 45%|████▌     | 90/200 [03:12<03:44,  2.04s/it]\n 46%|████▌     | 91/200 [03:13<02:44,  1.51s/it]\n 46%|████▌     | 92/200 [03:16<03:44,  2.08s/it]\n 46%|████▋     | 93/200 [03:16<02:43,  1.53s/it]\n 47%|████▋     | 94/200 [03:16<02:01,  1.15s/it]\n 48%|████▊     | 95/200 [03:20<03:13,  1.84s/it]\n 48%|████▊     | 96/200 [03:23<04:00,  2.31s/it]\n 48%|████▊     | 97/200 [03:27<04:35,  2.67s/it]\n 49%|████▉     | 98/200 [03:27<03:14,  1.91s/it]\n 50%|████▉     | 99/200 [03:27<02:23,  1.42s/it]\n 50%|█████     | 100/200 [03:27<01:47,  1.07s/it]\n 50%|█████     | 101/200 [03:28<01:22,  1.19it/s]\n 51%|█████     | 102/200 [03:28<01:05,  1.49it/s]\n 52%|█████▏    | 103/200 [03:31<02:24,  1.49s/it]\n 52%|█████▏    | 104/200 [03:35<03:18,  2.07s/it]\n 52%|█████▎    | 105/200 [03:35<02:24,  1.52s/it]\n 53%|█████▎    | 106/200 [03:35<01:47,  1.15s/it]\n 54%|█████▎    | 107/200 [03:36<01:22,  1.13it/s]\n 54%|█████▍    | 108/200 [03:39<02:30,  1.63s/it]\n 55%|█████▍    | 109/200 [03:42<03:15,  2.15s/it]\n 55%|█████▌    | 110/200 [03:43<02:22,  1.58s/it]\n 56%|█████▌    | 111/200 [03:46<03:11,  2.15s/it]\n 56%|█████▌    | 112/200 [03:46<02:15,  1.54s/it]\n 56%|█████▋    | 113/200 [03:47<01:40,  1.16s/it]\n 57%|█████▋    | 114/200 [03:47<01:16,  1.13it/s]\n 57%|█████▊    | 115/200 [03:47<00:59,  1.42it/s]\n 58%|█████▊    | 116/200 [03:50<02:06,  1.51s/it]\n 58%|█████▊    | 117/200 [03:54<02:52,  2.07s/it]\n 59%|█████▉    | 118/200 [03:57<03:24,  2.49s/it]\n 60%|█████▉    | 119/200 [04:01<03:43,  2.76s/it]\n 60%|██████    | 120/200 [04:01<02:40,  2.01s/it]\n 60%|██████    | 121/200 [04:04<03:13,  2.45s/it]\n 61%|██████    | 122/200 [04:08<03:33,  2.74s/it]\n 62%|██████▏   | 123/200 [04:08<02:33,  1.99s/it]\n 62%|██████▏   | 124/200 [04:12<03:04,  2.43s/it]\n 62%|██████▎   | 125/200 [04:15<03:25,  2.74s/it]\n 63%|██████▎   | 126/200 [04:15<02:27,  1.99s/it]\n 64%|██████▎   | 127/200 [04:19<02:55,  2.41s/it]\n 64%|██████▍   | 128/200 [04:19<02:07,  1.77s/it]\n 64%|██████▍   | 129/200 [04:19<01:30,  1.28s/it]\n 65%|██████▌   | 130/200 [04:19<01:08,  1.03it/s]\n 66%|██████▌   | 131/200 [04:20<00:52,  1.31it/s]\n 66%|██████▌   | 132/200 [04:23<01:46,  1.56s/it]\n 66%|██████▋   | 133/200 [04:23<01:18,  1.17s/it]\n 67%|██████▋   | 134/200 [04:27<02:02,  1.86s/it]\n 68%|██████▊   | 135/200 [04:30<02:34,  2.38s/it]\n 68%|██████▊   | 136/200 [04:30<01:49,  1.71s/it]\n 68%|██████▊   | 137/200 [04:31<01:20,  1.28s/it]\n 69%|██████▉   | 138/200 [04:31<01:00,  1.03it/s]\n 70%|██████▉   | 139/200 [04:34<01:43,  1.70s/it]\n 70%|███████   | 140/200 [04:35<01:15,  1.27s/it]\n 70%|███████   | 141/200 [04:35<00:57,  1.03it/s]\n 71%|███████   | 142/200 [04:35<00:44,  1.31it/s]\n 72%|███████▏  | 143/200 [04:39<01:29,  1.56s/it]\n 72%|███████▏  | 144/200 [04:42<01:58,  2.11s/it]\n 72%|███████▎  | 145/200 [04:42<01:25,  1.56s/it]\n 73%|███████▎  | 146/200 [04:43<01:03,  1.18s/it]\n 74%|███████▎  | 147/200 [04:43<00:48,  1.10it/s]\n 74%|███████▍  | 148/200 [04:46<01:26,  1.66s/it]\n 74%|███████▍  | 149/200 [04:50<01:51,  2.19s/it]\n 75%|███████▌  | 150/200 [04:50<01:18,  1.57s/it]\n 76%|███████▌  | 151/200 [04:53<01:43,  2.12s/it]\n 76%|███████▌  | 152/200 [04:57<02:01,  2.53s/it]\n 76%|███████▋  | 153/200 [05:00<02:11,  2.79s/it]\n 77%|███████▋  | 154/200 [05:03<02:15,  2.96s/it]\n 78%|███████▊  | 155/200 [05:04<01:34,  2.11s/it]\n 78%|███████▊  | 156/200 [05:04<01:08,  1.55s/it]\n 78%|███████▊  | 157/200 [05:07<01:30,  2.10s/it]\n 79%|███████▉  | 158/200 [05:11<01:45,  2.50s/it]\n 80%|███████▉  | 159/200 [05:14<01:54,  2.79s/it]\n 80%|████████  | 160/200 [05:14<01:19,  1.99s/it]\n 80%|████████  | 161/200 [05:14<00:57,  1.47s/it]\n 81%|████████  | 162/200 [05:15<00:42,  1.11s/it]\n 82%|████████▏ | 163/200 [05:15<00:31,  1.17it/s]\n 82%|████████▏ | 164/200 [05:15<00:24,  1.48it/s]\n 82%|████████▎ | 165/200 [05:16<00:19,  1.80it/s]\n 83%|████████▎ | 166/200 [05:19<00:48,  1.43s/it]\n 84%|████████▎ | 167/200 [05:19<00:35,  1.08s/it]\n 84%|████████▍ | 168/200 [05:19<00:25,  1.26it/s]\n 84%|████████▍ | 169/200 [05:20<00:19,  1.56it/s]\n 85%|████████▌ | 170/200 [05:23<00:45,  1.51s/it]\n 86%|████████▌ | 171/200 [05:23<00:31,  1.09s/it]\n 86%|████████▌ | 172/200 [05:27<00:51,  1.84s/it]\n 86%|████████▋ | 173/200 [05:30<01:03,  2.33s/it]\n 87%|████████▋ | 174/200 [05:34<01:08,  2.63s/it]\n 88%|████████▊ | 175/200 [05:34<00:46,  1.87s/it]\n 88%|████████▊ | 176/200 [05:34<00:33,  1.39s/it]\n 88%|████████▊ | 177/200 [05:37<00:45,  1.98s/it]\n 89%|████████▉ | 178/200 [05:41<00:53,  2.44s/it]\n 90%|████████▉ | 179/200 [05:41<00:36,  1.74s/it]\n 90%|█████████ | 180/200 [05:41<00:25,  1.30s/it]\n 90%|█████████ | 181/200 [05:45<00:36,  1.93s/it]\n 91%|█████████ | 182/200 [05:48<00:42,  2.38s/it]\n 92%|█████████▏| 183/200 [05:52<00:46,  2.72s/it]\n 92%|█████████▏| 184/200 [05:55<00:46,  2.93s/it]\n 92%|█████████▎| 185/200 [05:59<00:46,  3.07s/it]\n 93%|█████████▎| 186/200 [05:59<00:30,  2.19s/it]\n 94%|█████████▎| 187/200 [05:59<00:20,  1.61s/it]\n 94%|█████████▍| 188/200 [06:02<00:26,  2.18s/it]\n 94%|█████████▍| 189/200 [06:06<00:28,  2.58s/it]\n 95%|█████████▌| 190/200 [06:06<00:18,  1.88s/it]\n 96%|█████████▌| 191/200 [06:06<00:12,  1.40s/it]\n 96%|█████████▌| 192/200 [06:10<00:16,  2.02s/it]\n 96%|█████████▋| 193/200 [06:10<00:10,  1.50s/it]\n 97%|█████████▋| 194/200 [06:11<00:06,  1.14s/it]\n 98%|█████████▊| 195/200 [06:14<00:09,  1.88s/it]\n 98%|█████████▊| 196/200 [06:18<00:09,  2.41s/it]\n 98%|█████████▊| 197/200 [06:18<00:05,  1.77s/it]\n 99%|█████████▉| 198/200 [06:18<00:02,  1.32s/it]\n100%|█████████▉| 199/200 [06:19<00:01,  1.01s/it]\n100%|██████████| 200/200 [06:22<00:00,  1.81s/it]\n100%|██████████| 200/200 [06:22<00:00,  1.91s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752022542/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_1752022542/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_1752022542/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_1752022542/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 : 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 : 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 (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 : 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 : 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 : 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 : 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 : 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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 382.7762773036957\nerrors 95\nmean length: 1.575\n\nthroughput (request / second): 0.5224984197265691\nthroughput (character / second): 0.8229350110693464\naverage request duration (s) 1.9137735676765442\n50%ile request duration (s) 3.351220726966858\n75%ile request duration (s) 3.4253549575805664\n90%ile request duration (s) 3.504140281677246\n95%ile request duration (s) 3.5420788407325743\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-89339-v1-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-89339-v1-profiler
Service chaiml-llama3-200m-v2-t-89339-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.81s
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-89339-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.17s
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-llama3-200m-v2-t-89339-v1-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-89339-v1-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-89339-v1-profiler ready after 40.520259141922s
Pipeline stage MKMLProfilerDeployer completed in 41.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9:/code/chaiverse_profiler_1752023045 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752023045 && 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_1752023045/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9:/code/chaiverse_profiler_1752023452 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752023452 && 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_1752023452/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9:/code/chaiverse_profiler_1752023883 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deplokqfm9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752023883 && 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_1752023883/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<00:51,  3.87it/s]\n  1%|          | 2/200 [00:03<07:00,  2.12s/it]\n  2%|▏         | 3/200 [00:07<09:00,  2.74s/it]\n  2%|▏         | 4/200 [00:10<09:53,  3.03s/it]\n  2%|▎         | 5/200 [00:10<06:35,  2.03s/it]\n  3%|▎         | 6/200 [00:11<04:37,  1.43s/it]\n  4%|▎         | 7/200 [00:14<06:46,  2.10s/it]\n  4%|▍         | 8/200 [00:18<08:07,  2.54s/it]\n  4%|▍         | 9/200 [00:18<05:40,  1.78s/it]\n  5%|▌         | 10/200 [00:21<07:25,  2.34s/it]\n  6%|▌         | 11/200 [00:25<08:32,  2.71s/it]\n  6%|▌         | 12/200 [00:28<09:13,  2.94s/it]\n  6%|▋         | 13/200 [00:32<09:38,  3.09s/it]\n  7%|▋         | 14/200 [00:35<09:54,  3.20s/it]\n  8%|▊         | 15/200 [00:39<10:06,  3.28s/it]\n  8%|▊         | 16/200 [00:42<10:11,  3.32s/it]\n  8%|▊         | 17/200 [00:42<07:12,  2.36s/it]\n  9%|▉         | 18/200 [00:46<08:14,  2.72s/it]\n 10%|▉         | 19/200 [00:46<05:56,  1.97s/it]\n 10%|█         | 20/200 [00:46<04:22,  1.46s/it]\n 10%|█         | 21/200 [00:47<03:16,  1.10s/it]\n 11%|█         | 22/200 [00:47<02:30,  1.18it/s]\n 12%|█▏        | 23/200 [00:47<01:58,  1.49it/s]\n 12%|█▏        | 24/200 [00:51<04:23,  1.50s/it]\n 12%|█▎        | 25/200 [00:51<03:16,  1.12s/it]\n 13%|█▎        | 26/200 [00:51<02:30,  1.16it/s]\n 14%|█▎        | 27/200 [00:55<04:47,  1.66s/it]\n 14%|█▍        | 28/200 [00:55<03:34,  1.25s/it]\n 14%|█▍        | 29/200 [00:58<05:25,  1.90s/it]\n 15%|█▌        | 30/200 [01:02<06:40,  2.36s/it]\n 16%|█▌        | 31/200 [01:02<04:44,  1.69s/it]\n 16%|█▌        | 32/200 [01:02<03:31,  1.26s/it]\n 16%|█▋        | 33/200 [01:06<05:24,  1.94s/it]\n 17%|█▋        | 34/200 [01:09<06:36,  2.39s/it]\n 18%|█▊        | 35/200 [01:13<07:34,  2.75s/it]\n 18%|█▊        | 36/200 [01:16<08:07,  2.97s/it]\n 18%|█▊        | 37/200 [01:20<08:31,  3.14s/it]\n 19%|█▉        | 38/200 [01:23<08:41,  3.22s/it]\n 20%|█▉        | 39/200 [01:23<06:08,  2.29s/it]\n 20%|██        | 40/200 [01:27<07:08,  2.68s/it]\n 20%|██        | 41/200 [01:27<05:05,  1.92s/it]\n 21%|██        | 42/200 [01:27<03:44,  1.42s/it]\n 22%|██▏       | 43/200 [01:27<02:48,  1.07s/it]\n 22%|██▏       | 44/200 [01:31<04:38,  1.79s/it]\n 22%|██▎       | 45/200 [01:31<03:25,  1.33s/it]\n 23%|██▎       | 46/200 [01:31<02:37,  1.02s/it]\n 24%|██▎       | 47/200 [01:32<02:02,  1.25it/s]\n 24%|██▍       | 48/200 [01:32<01:37,  1.55it/s]\n 24%|██▍       | 49/200 [01:36<03:48,  1.52s/it]\n 25%|██▌       | 50/200 [01:39<05:20,  2.14s/it]\n 26%|██▌       | 51/200 [01:43<06:18,  2.54s/it]\n 26%|██▌       | 52/200 [01:46<07:00,  2.84s/it]\n 26%|██▋       | 53/200 [01:50<07:29,  3.06s/it]\n 27%|██▋       | 54/200 [01:53<07:47,  3.21s/it]\n 28%|██▊       | 55/200 [01:57<08:00,  3.31s/it]\n 28%|██▊       | 56/200 [01:57<05:46,  2.41s/it]\n 28%|██▊       | 57/200 [01:57<04:12,  1.77s/it]\n 29%|██▉       | 58/200 [01:58<03:08,  1.32s/it]\n 30%|██▉       | 59/200 [02:01<04:44,  2.02s/it]\n 30%|███       | 60/200 [02:05<05:47,  2.48s/it]\n 30%|███       | 61/200 [02:06<04:29,  1.94s/it]\n 31%|███       | 62/200 [02:09<05:47,  2.52s/it]\n 32%|███▏      | 63/200 [02:13<06:34,  2.88s/it]\n 32%|███▏      | 64/200 [02:17<07:06,  3.14s/it]\n 32%|███▎      | 65/200 [02:17<05:09,  2.29s/it]\n 33%|███▎      | 66/200 [02:21<06:06,  2.73s/it]\n 34%|███▎      | 67/200 [02:21<04:26,  2.01s/it]\n 34%|███▍      | 68/200 [02:22<03:18,  1.51s/it]\n 34%|███▍      | 69/200 [02:22<02:31,  1.16s/it]\n 35%|███▌      | 70/200 [02:26<04:08,  1.91s/it]\n 36%|███▌      | 71/200 [02:26<03:05,  1.44s/it]\n 36%|███▌      | 72/200 [02:26<02:14,  1.05s/it]\n 36%|███▋      | 73/200 [02:30<04:02,  1.91s/it]\n 37%|███▋      | 74/200 [02:30<02:53,  1.38s/it]\n 38%|███▊      | 75/200 [02:30<02:12,  1.06s/it]\n 38%|███▊      | 76/200 [02:31<01:43,  1.19it/s]\n 38%|███▊      | 77/200 [02:31<01:24,  1.46it/s]\n 39%|███▉      | 78/200 [02:31<01:10,  1.74it/s]\n 40%|███▉      | 79/200 [02:35<03:03,  1.51s/it]\n 40%|████      | 80/200 [02:36<02:19,  1.17s/it]\n 40%|████      | 81/200 [02:39<03:49,  1.93s/it]\n 41%|████      | 82/200 [02:43<04:49,  2.45s/it]\n 42%|████▏     | 83/200 [02:47<05:29,  2.82s/it]\n 42%|████▏     | 84/200 [02:50<05:57,  3.08s/it]\n 42%|████▎     | 85/200 [02:51<04:19,  2.25s/it]\n 43%|████▎     | 86/200 [02:51<03:04,  1.62s/it]\n 44%|████▎     | 87/200 [02:51<02:19,  1.23s/it]\n 44%|████▍     | 88/200 [02:51<01:46,  1.05it/s]\n 44%|████▍     | 89/200 [02:55<03:18,  1.79s/it]\n 45%|████▌     | 90/200 [02:55<02:28,  1.35s/it]\n 46%|████▌     | 91/200 [02:59<03:44,  2.06s/it]\n 46%|████▌     | 92/200 [02:59<02:45,  1.53s/it]\n 46%|████▋     | 93/200 [03:00<02:04,  1.17s/it]\n 47%|████▋     | 94/200 [03:03<03:24,  1.93s/it]\n 48%|████▊     | 95/200 [03:07<04:23,  2.51s/it]\n 48%|████▊     | 96/200 [03:11<04:57,  2.86s/it]\n 48%|████▊     | 97/200 [03:11<03:35,  2.09s/it]\n 49%|████▉     | 98/200 [03:15<04:22,  2.57s/it]\n 50%|████▉     | 99/200 [03:15<03:11,  1.89s/it]\n 50%|█████     | 100/200 [03:19<04:04,  2.45s/it]\n 50%|█████     | 101/200 [03:23<04:38,  2.81s/it]\n 51%|█████     | 102/200 [03:26<04:59,  3.06s/it]\n 52%|█████▏    | 103/200 [03:30<05:12,  3.22s/it]\n 52%|█████▏    | 104/200 [03:34<05:27,  3.41s/it]\n 52%|█████▎    | 105/200 [03:38<05:33,  3.51s/it]\n 53%|█████▎    | 106/200 [03:38<03:54,  2.50s/it]\n 54%|█████▎    | 107/200 [03:38<02:51,  1.85s/it]\n 54%|█████▍    | 108/200 [03:38<02:07,  1.38s/it]\n 55%|█████▍    | 109/200 [03:39<01:36,  1.06s/it]\n 55%|█████▌    | 110/200 [03:39<01:15,  1.19it/s]\n 56%|█████▌    | 111/200 [03:43<02:30,  1.69s/it]\n 56%|█████▌    | 112/200 [03:43<01:52,  1.27s/it]\n 56%|█████▋    | 113/200 [03:43<01:26,  1.00it/s]\n 57%|█████▋    | 114/200 [03:47<02:37,  1.84s/it]\n 57%|█████▊    | 115/200 [03:47<01:58,  1.39s/it]\n 58%|█████▊    | 116/200 [03:51<02:54,  2.08s/it]\n 58%|█████▊    | 117/200 [03:51<02:04,  1.50s/it]\n 59%|█████▉    | 118/200 [03:55<03:03,  2.24s/it]\n 60%|█████▉    | 119/200 [03:59<03:36,  2.68s/it]\n 60%|██████    | 120/200 [03:59<02:33,  1.91s/it]\n 60%|██████    | 121/200 [03:59<01:54,  1.45s/it]\n 61%|██████    | 122/200 [04:03<02:46,  2.13s/it]\n 62%|██████▏   | 123/200 [04:07<03:22,  2.62s/it]\n 62%|██████▏   | 124/200 [04:07<02:26,  1.93s/it]\n 62%|██████▎   | 125/200 [04:07<01:47,  1.43s/it]\n 63%|██████▎   | 126/200 [04:08<01:21,  1.10s/it]\n 64%|██████▎   | 127/200 [04:11<02:14,  1.85s/it]\n 64%|██████▍   | 128/200 [04:15<02:52,  2.39s/it]\n 64%|██████▍   | 129/200 [04:19<03:16,  2.77s/it]\n 65%|██████▌   | 130/200 [04:19<02:22,  2.03s/it]\n 66%|██████▌   | 131/200 [04:23<02:54,  2.52s/it]\n 66%|██████▌   | 132/200 [04:26<03:15,  2.87s/it]\n 66%|██████▋   | 133/200 [04:27<02:21,  2.11s/it]\n 67%|██████▋   | 134/200 [04:30<02:49,  2.57s/it]\n 68%|██████▊   | 135/200 [04:34<03:08,  2.91s/it]\n 68%|██████▊   | 136/200 [04:38<03:20,  3.14s/it]\n 68%|██████▊   | 137/200 [04:38<02:24,  2.29s/it]\n 69%|██████▉   | 138/200 [04:42<02:48,  2.72s/it]\n 70%|██████▉   | 139/200 [04:45<03:03,  3.01s/it]\n 70%|███████   | 140/200 [04:49<03:12,  3.20s/it]\n 70%|███████   | 141/200 [04:49<02:17,  2.33s/it]\n 71%|███████   | 142/200 [04:53<02:38,  2.73s/it]\n 72%|███████▏  | 143/200 [04:57<02:51,  3.02s/it]\n 72%|███████▏  | 144/200 [05:00<02:59,  3.21s/it]\n 72%|███████▎  | 145/200 [05:01<02:08,  2.33s/it]\n 73%|███████▎  | 146/200 [05:04<02:29,  2.77s/it]\n 74%|███████▎  | 147/200 [05:08<02:40,  3.02s/it]\n 74%|███████▍  | 148/200 [05:12<02:46,  3.20s/it]\n 74%|███████▍  | 149/200 [05:15<02:50,  3.35s/it]\n 75%|███████▌  | 150/200 [05:19<02:52,  3.44s/it]\n 76%|███████▌  | 151/200 [05:23<02:52,  3.52s/it]\n 76%|███████▌  | 152/200 [05:26<02:51,  3.58s/it]\n 76%|███████▋  | 153/200 [05:27<02:01,  2.59s/it]\n 77%|███████▋  | 154/200 [05:27<01:27,  1.90s/it]\n 78%|███████▊  | 155/200 [05:27<01:03,  1.42s/it]\n 78%|███████▊  | 156/200 [05:28<00:47,  1.09s/it]\n 78%|███████▊  | 157/200 [05:31<01:20,  1.88s/it]\n 79%|███████▉  | 158/200 [05:35<01:41,  2.41s/it]\n 80%|███████▉  | 159/200 [05:39<01:54,  2.80s/it]\n 80%|████████  | 160/200 [05:39<01:19,  2.00s/it]\n 80%|████████  | 161/200 [05:39<00:58,  1.50s/it]\n 81%|████████  | 162/200 [05:43<01:21,  2.14s/it]\n 82%|████████▏ | 163/200 [05:47<01:36,  2.61s/it]\n 82%|████████▏ | 164/200 [05:47<01:08,  1.90s/it]\n 82%|████████▎ | 165/200 [05:47<00:50,  1.43s/it]\n 83%|████████▎ | 166/200 [05:47<00:37,  1.09s/it]\n 84%|████████▎ | 167/200 [05:48<00:28,  1.17it/s]\n 84%|████████▍ | 168/200 [05:48<00:22,  1.45it/s]\n 84%|████████▍ | 169/200 [05:52<00:49,  1.59s/it]\n 85%|████████▌ | 170/200 [05:52<00:36,  1.21s/it]\n 86%|████████▌ | 171/200 [05:56<00:56,  1.94s/it]\n 86%|████████▌ | 172/200 [05:56<00:40,  1.45s/it]\n 86%|████████▋ | 173/200 [06:00<00:58,  2.15s/it]\n 87%|████████▋ | 174/200 [06:03<01:07,  2.58s/it]\n 88%|████████▊ | 175/200 [06:07<01:13,  2.94s/it]\n 88%|████████▊ | 176/200 [06:07<00:51,  2.15s/it]\n 88%|████████▊ | 177/200 [06:11<01:00,  2.62s/it]\n 89%|████████▉ | 178/200 [06:15<01:04,  2.92s/it]\n 90%|████████▉ | 179/200 [06:18<01:06,  3.14s/it]\n 90%|█████████ | 180/200 [06:22<01:05,  3.29s/it]\n 90%|█████████ | 181/200 [06:26<01:04,  3.42s/it]\n 91%|█████████ | 182/200 [06:26<00:43,  2.43s/it]\n 92%|█████████▏| 183/200 [06:26<00:30,  1.80s/it]\n 92%|█████████▏| 184/200 [06:30<00:37,  2.36s/it]\n 92%|█████████▎| 185/200 [06:33<00:40,  2.73s/it]\n 93%|█████████▎| 186/200 [06:37<00:42,  3.04s/it]\n 94%|█████████▎| 187/200 [06:37<00:28,  2.17s/it]\n 94%|█████████▍| 188/200 [06:41<00:32,  2.67s/it]\n 94%|█████████▍| 189/200 [06:41<00:21,  1.91s/it]\n 95%|█████████▌| 190/200 [06:42<00:14,  1.43s/it]\n 96%|█████████▌| 191/200 [06:42<00:09,  1.09s/it]\n 96%|█████████▌| 192/200 [06:46<00:14,  1.86s/it]\n 96%|█████████▋| 193/200 [06:50<00:17,  2.48s/it]\n 97%|█████████▋| 194/200 [06:50<00:10,  1.78s/it]\n 98%|█████████▊| 195/200 [06:53<00:11,  2.38s/it]\n 98%|█████████▊| 196/200 [06:54<00:06,  1.70s/it]\n 98%|█████████▊| 197/200 [06:54<00:03,  1.28s/it]\n 99%|█████████▉| 198/200 [06:58<00:03,  1.98s/it]\n100%|█████████▉| 199/200 [06:58<00:01,  1.47s/it]\n100%|██████████| 200/200 [07:02<00:00,  2.19s/it]\n100%|██████████| 200/200 [07:02<00:00,  2.11s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752023883/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_1752023883/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_1752023883/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_1752023883/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 (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 : 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 : 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 (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 : 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 (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 : 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 : 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 (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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 422.1686987876892\nerrors 91\nmean length: 1.635\n\nthroughput (request / second): 0.4737442652056519\nthroughput (character / second): 0.7745718736112408\naverage request duration (s) 2.1106850504875183\n50%ile request duration (s) 3.4511640071868896\n75%ile request duration (s) 3.6694313883781433\n90%ile request duration (s) 3.7333362102508545\n95%ile request duration (s) 3.7847492933273315\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-89339-v1-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-89339-v1-profiler
Service chaiml-llama3-200m-v2-t-89339-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.01s
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-89339-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.44s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama3-200m-v2-t-89339-v1-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-89339-v1-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-89339-v1-profiler ready after 50.57879972457886s
Pipeline stage MKMLProfilerDeployer completed in 51.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws:/code/chaiverse_profiler_1752024434 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752024434 && 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_1752024434/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws:/code/chaiverse_profiler_1752024844 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752024844 && 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_1752024844/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws:/code/chaiverse_profiler_1752025251 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v6eb9f09c91e5b33a80fd92828c4cf647-deploprfws --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752025251 && 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_1752025251/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<11:40,  3.52s/it]\n  1%|          | 2/200 [00:07<11:37,  3.52s/it]\n  2%|▏         | 3/200 [00:07<06:43,  2.05s/it]\n  2%|▏         | 4/200 [00:07<04:24,  1.35s/it]\n  2%|▎         | 5/200 [00:11<06:54,  2.13s/it]\n  3%|▎         | 6/200 [00:14<08:39,  2.68s/it]\n  4%|▎         | 7/200 [00:18<09:29,  2.95s/it]\n  4%|▍         | 8/200 [00:21<09:58,  3.12s/it]\n  4%|▍         | 9/200 [00:25<10:17,  3.23s/it]\n  5%|▌         | 10/200 [00:25<07:12,  2.28s/it]\n  6%|▌         | 11/200 [00:25<05:14,  1.66s/it]\n  6%|▌         | 12/200 [00:26<03:53,  1.24s/it]\n  6%|▋         | 13/200 [00:26<02:57,  1.05it/s]\n  7%|▋         | 14/200 [00:26<02:18,  1.35it/s]\n  8%|▊         | 15/200 [00:26<01:51,  1.66it/s]\n  8%|▊         | 16/200 [00:30<04:30,  1.47s/it]\n  8%|▊         | 17/200 [00:33<06:17,  2.06s/it]\n  9%|▉         | 18/200 [00:37<07:34,  2.50s/it]\n 10%|▉         | 19/200 [00:40<08:24,  2.79s/it]\n 10%|█         | 20/200 [00:44<08:58,  2.99s/it]\n 10%|█         | 21/200 [00:44<06:30,  2.18s/it]\n 11%|█         | 22/200 [00:47<07:38,  2.57s/it]\n 12%|█▏        | 23/200 [00:51<08:22,  2.84s/it]\n 12%|█▏        | 24/200 [00:55<08:57,  3.05s/it]\n 12%|█▎        | 25/200 [00:58<09:21,  3.21s/it]\n 13%|█▎        | 26/200 [01:02<09:32,  3.29s/it]\n 14%|█▎        | 27/200 [01:05<09:44,  3.38s/it]\n 14%|█▍        | 28/200 [01:09<09:45,  3.40s/it]\n 14%|█▍        | 29/200 [01:09<06:54,  2.42s/it]\n 15%|█▌        | 30/200 [01:09<05:01,  1.77s/it]\n 16%|█▌        | 31/200 [01:12<06:25,  2.28s/it]\n 16%|█▌        | 32/200 [01:16<07:21,  2.63s/it]\n 16%|█▋        | 33/200 [01:19<08:01,  2.88s/it]\n 17%|█▋        | 34/200 [01:20<05:47,  2.09s/it]\n 18%|█▊        | 35/200 [01:23<06:57,  2.53s/it]\n 18%|█▊        | 36/200 [01:27<07:47,  2.85s/it]\n 18%|█▊        | 37/200 [01:30<08:13,  3.03s/it]\n 19%|█▉        | 38/200 [01:30<05:49,  2.16s/it]\n 20%|█▉        | 39/200 [01:31<04:16,  1.59s/it]\n 20%|██        | 40/200 [01:34<05:43,  2.15s/it]\n 20%|██        | 41/200 [01:38<06:49,  2.57s/it]\n 21%|██        | 42/200 [01:38<04:50,  1.84s/it]\n 22%|██▏       | 43/200 [01:41<06:06,  2.33s/it]\n 22%|██▏       | 44/200 [01:42<04:26,  1.71s/it]\n 22%|██▎       | 45/200 [01:45<05:48,  2.25s/it]\n 23%|██▎       | 46/200 [01:49<06:49,  2.66s/it]\n 24%|██▎       | 47/200 [01:49<04:50,  1.90s/it]\n 24%|██▍       | 48/200 [01:52<06:04,  2.40s/it]\n 24%|██▍       | 49/200 [01:53<04:24,  1.75s/it]\n 25%|██▌       | 50/200 [01:56<05:42,  2.28s/it]\n 26%|██▌       | 51/200 [02:00<06:39,  2.68s/it]\n 26%|██▌       | 52/200 [02:03<07:12,  2.92s/it]\n 26%|██▋       | 53/200 [02:03<05:06,  2.08s/it]\n 27%|██▋       | 54/200 [02:04<03:44,  1.54s/it]\n 28%|██▊       | 55/200 [02:04<02:48,  1.16s/it]\n 28%|██▊       | 56/200 [02:04<02:08,  1.12it/s]\n 28%|██▊       | 57/200 [02:04<01:41,  1.41it/s]\n 29%|██▉       | 58/200 [02:05<01:22,  1.73it/s]\n 30%|██▉       | 59/200 [02:08<03:26,  1.46s/it]\n 30%|███       | 60/200 [02:08<02:34,  1.10s/it]\n 30%|███       | 61/200 [02:12<04:12,  1.82s/it]\n 31%|███       | 62/200 [02:12<03:00,  1.31s/it]\n 32%|███▏      | 63/200 [02:12<02:16,  1.00it/s]\n 32%|███▏      | 64/200 [02:16<04:04,  1.79s/it]\n 32%|███▎      | 65/200 [02:19<05:10,  2.30s/it]\n 33%|███▎      | 66/200 [02:23<05:55,  2.65s/it]\n 34%|███▎      | 67/200 [02:23<04:11,  1.89s/it]\n 34%|███▍      | 68/200 [02:27<05:17,  2.41s/it]\n 34%|███▍      | 69/200 [02:30<06:00,  2.75s/it]\n 35%|███▌      | 70/200 [02:30<04:15,  1.97s/it]\n 36%|███▌      | 71/200 [02:31<03:07,  1.45s/it]\n 36%|███▌      | 72/200 [02:31<02:20,  1.10s/it]\n 36%|███▋      | 73/200 [02:34<03:49,  1.81s/it]\n 37%|███▋      | 74/200 [02:35<02:48,  1.34s/it]\n 38%|███▊      | 75/200 [02:38<04:08,  1.99s/it]\n 38%|███▊      | 76/200 [02:38<03:01,  1.46s/it]\n 38%|███▊      | 77/200 [02:39<02:15,  1.10s/it]\n 39%|███▉      | 78/200 [02:39<01:44,  1.17it/s]\n 40%|███▉      | 79/200 [02:39<01:21,  1.48it/s]\n 40%|████      | 80/200 [02:39<01:06,  1.79it/s]\n 40%|████      | 81/200 [02:43<02:50,  1.43s/it]\n 41%|████      | 82/200 [02:43<02:07,  1.08s/it]\n 42%|████▏     | 83/200 [02:43<01:37,  1.20it/s]\n 42%|████▏     | 84/200 [02:47<03:08,  1.62s/it]\n 42%|████▎     | 85/200 [02:50<04:12,  2.20s/it]\n 43%|████▎     | 86/200 [02:54<04:54,  2.58s/it]\n 44%|████▎     | 87/200 [02:54<03:33,  1.89s/it]\n 44%|████▍     | 88/200 [02:58<04:26,  2.38s/it]\n 44%|████▍     | 89/200 [03:01<05:01,  2.72s/it]\n 45%|████▌     | 90/200 [03:05<05:22,  2.93s/it]\n 46%|████▌     | 91/200 [03:08<05:37,  3.09s/it]\n 46%|████▌     | 92/200 [03:12<05:47,  3.21s/it]\n 46%|████▋     | 93/200 [03:12<04:04,  2.29s/it]\n 47%|████▋     | 94/200 [03:15<04:39,  2.64s/it]\n 48%|████▊     | 95/200 [03:15<03:22,  1.93s/it]\n 48%|████▊     | 96/200 [03:16<02:28,  1.43s/it]\n 48%|████▊     | 97/200 [03:19<03:30,  2.05s/it]\n 49%|████▉     | 98/200 [03:19<02:34,  1.51s/it]\n 50%|████▉     | 99/200 [03:23<03:32,  2.11s/it]\n 50%|█████     | 100/200 [03:26<04:10,  2.50s/it]\n 50%|█████     | 101/200 [03:30<04:34,  2.78s/it]\n 51%|█████     | 102/200 [03:33<04:56,  3.03s/it]\n 52%|█████▏    | 103/200 [03:37<05:05,  3.15s/it]\n 52%|█████▏    | 104/200 [03:37<03:35,  2.24s/it]\n 52%|█████▎    | 105/200 [03:37<02:36,  1.65s/it]\n 53%|█████▎    | 106/200 [03:38<01:55,  1.23s/it]\n 54%|█████▎    | 107/200 [03:41<02:57,  1.91s/it]\n 54%|█████▍    | 108/200 [03:44<03:39,  2.38s/it]\n 55%|█████▍    | 109/200 [03:45<02:38,  1.74s/it]\n 55%|█████▌    | 110/200 [03:48<03:21,  2.24s/it]\n 56%|█████▌    | 111/200 [03:48<02:26,  1.65s/it]\n 56%|█████▌    | 112/200 [03:52<03:12,  2.19s/it]\n 56%|█████▋    | 113/200 [03:55<03:45,  2.59s/it]\n 57%|█████▋    | 114/200 [03:59<04:06,  2.87s/it]\n 57%|█████▊    | 115/200 [03:59<02:57,  2.08s/it]\n 58%|█████▊    | 116/200 [04:03<03:29,  2.49s/it]\n 58%|█████▊    | 117/200 [04:06<03:53,  2.81s/it]\n 59%|█████▉    | 118/200 [04:10<04:05,  3.00s/it]\n 60%|█████▉    | 119/200 [04:13<04:13,  3.13s/it]\n 60%|██████    | 120/200 [04:17<04:23,  3.30s/it]\n 60%|██████    | 121/200 [04:17<03:05,  2.35s/it]\n 61%|██████    | 122/200 [04:17<02:13,  1.72s/it]\n 62%|██████▏   | 123/200 [04:21<02:52,  2.23s/it]\n 62%|██████▏   | 124/200 [04:21<02:04,  1.64s/it]\n 62%|██████▎   | 125/200 [04:24<02:44,  2.20s/it]\n 63%|██████▎   | 126/200 [04:28<03:12,  2.60s/it]\n 64%|██████▎   | 127/200 [04:31<03:29,  2.87s/it]\n 64%|██████▍   | 128/200 [04:35<03:41,  3.07s/it]\n 64%|██████▍   | 129/200 [04:38<03:47,  3.20s/it]\n 65%|██████▌   | 130/200 [04:42<03:46,  3.24s/it]\n 66%|██████▌   | 131/200 [04:42<02:42,  2.35s/it]\n 66%|██████▌   | 132/200 [04:42<01:57,  1.73s/it]\n 66%|██████▋   | 133/200 [04:46<02:31,  2.26s/it]\n 67%|██████▋   | 134/200 [04:49<02:55,  2.66s/it]\n 68%|██████▊   | 135/200 [04:49<02:03,  1.90s/it]\n 68%|██████▊   | 136/200 [04:53<02:31,  2.37s/it]\n 68%|██████▊   | 137/200 [04:53<01:50,  1.75s/it]\n 69%|██████▉   | 138/200 [04:57<02:20,  2.27s/it]\n 70%|██████▉   | 139/200 [05:00<02:44,  2.69s/it]\n 70%|███████   | 140/200 [05:01<01:55,  1.93s/it]\n 70%|███████   | 141/200 [05:01<01:24,  1.43s/it]\n 71%|███████   | 142/200 [05:04<01:58,  2.04s/it]\n 72%|███████▏  | 143/200 [05:08<02:23,  2.52s/it]\n 72%|███████▏  | 144/200 [05:08<01:40,  1.80s/it]\n 72%|███████▎  | 145/200 [05:12<02:10,  2.38s/it]\n 73%|███████▎  | 146/200 [05:15<02:27,  2.73s/it]\n 74%|███████▎  | 147/200 [05:15<01:43,  1.95s/it]\n 74%|███████▍  | 148/200 [05:19<02:04,  2.39s/it]\n 74%|███████▍  | 149/200 [05:19<01:29,  1.75s/it]\n 75%|███████▌  | 150/200 [05:19<01:05,  1.31s/it]\n 76%|███████▌  | 151/200 [05:20<00:49,  1.00s/it]\n 76%|███████▌  | 152/200 [05:20<00:37,  1.27it/s]\n 76%|███████▋  | 153/200 [05:23<01:15,  1.60s/it]\n 77%|███████▋  | 154/200 [05:24<00:55,  1.20s/it]\n 78%|███████▊  | 155/200 [05:27<01:24,  1.88s/it]\n 78%|███████▊  | 156/200 [05:31<01:44,  2.37s/it]\n 78%|███████▊  | 157/200 [05:31<01:14,  1.74s/it]\n 79%|███████▉  | 158/200 [05:34<01:35,  2.27s/it]\n 80%|███████▉  | 159/200 [05:38<01:48,  2.64s/it]\n 80%|████████  | 160/200 [05:38<01:17,  1.93s/it]\n 80%|████████  | 161/200 [05:38<00:54,  1.39s/it]\n 81%|████████  | 162/200 [05:39<00:40,  1.06s/it]\n 82%|████████▏ | 163/200 [05:42<01:06,  1.78s/it]\n 82%|████████▏ | 164/200 [05:42<00:47,  1.32s/it]\n 82%|████████▎ | 165/200 [05:43<00:35,  1.01s/it]\n 83%|████████▎ | 166/200 [05:46<00:59,  1.76s/it]\n 84%|████████▎ | 167/200 [05:46<00:43,  1.31s/it]\n 84%|████████▍ | 168/200 [05:47<00:31,  1.00it/s]\n 84%|████████▍ | 169/200 [05:50<00:53,  1.73s/it]\n 85%|████████▌ | 170/200 [05:54<01:09,  2.30s/it]\n 86%|████████▌ | 171/200 [05:54<00:47,  1.65s/it]\n 86%|████████▌ | 172/200 [05:57<01:02,  2.22s/it]\n 86%|████████▋ | 173/200 [05:58<00:43,  1.63s/it]\n 87%|████████▋ | 174/200 [06:01<00:57,  2.21s/it]\n 88%|████████▊ | 175/200 [06:05<01:05,  2.61s/it]\n 88%|████████▊ | 176/200 [06:08<01:09,  2.89s/it]\n 88%|████████▊ | 177/200 [06:12<01:10,  3.05s/it]\n 89%|████████▉ | 178/200 [06:12<00:47,  2.17s/it]\n 90%|████████▉ | 179/200 [06:12<00:33,  1.60s/it]\n 90%|█████████ | 180/200 [06:12<00:24,  1.20s/it]\n 90%|█████████ | 181/200 [06:13<00:17,  1.08it/s]\n 91%|█████████ | 182/200 [06:16<00:30,  1.69s/it]\n 92%|█████████▏| 183/200 [06:20<00:37,  2.23s/it]\n 92%|█████████▏| 184/200 [06:23<00:41,  2.62s/it]\n 92%|█████████▎| 185/200 [06:27<00:43,  2.88s/it]\n 93%|█████████▎| 186/200 [06:30<00:42,  3.06s/it]\n 94%|█████████▎| 187/200 [06:34<00:41,  3.17s/it]\n 94%|█████████▍| 188/200 [06:34<00:27,  2.26s/it]\n 94%|█████████▍| 189/200 [06:37<00:29,  2.68s/it]\n 95%|█████████▌| 190/200 [06:38<00:19,  1.92s/it]\n 96%|█████████▌| 191/200 [06:38<00:12,  1.43s/it]\n 96%|█████████▌| 192/200 [06:41<00:16,  2.06s/it]\n 96%|█████████▋| 193/200 [06:45<00:17,  2.55s/it]\n 97%|█████████▋| 194/200 [06:45<00:10,  1.82s/it]\n 98%|█████████▊| 195/200 [06:45<00:06,  1.36s/it]\n 98%|█████████▊| 196/200 [06:46<00:04,  1.03s/it]\n 98%|█████████▊| 197/200 [06:46<00:02,  1.26it/s]\n 99%|█████████▉| 198/200 [06:49<00:03,  1.59s/it]\n100%|█████████▉| 199/200 [06:53<00:02,  2.14s/it]\n100%|██████████| 200/200 [06:56<00:00,  2.57s/it]\n100%|██████████| 200/200 [06:56<00:00,  2.08s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1752025251/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_1752025251/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_1752025251/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_1752025251/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 (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 : 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 : 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 : 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 (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 : 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 : 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 : 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 : 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 (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 : 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): 416.9459128379822\nerrors 87\nmean length: 1.695\n\nthroughput (request / second): 0.4796785238609989\nthroughput (character / second): 0.8130550979443931\naverage request duration (s) 2.084541049003601\n50%ile request duration (s) 3.436462879180908\n75%ile request duration (s) 3.50657194852829\n90%ile request duration (s) 3.5677316427230834\n95%ile request duration (s) 3.6114029765129088\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-89339-v1-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-89339-v1-profiler
Service chaiml-llama3-200m-v2-t-89339-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.51s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_89339_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama3-200m-v2-t_89339_v1 status is now torndown due to DeploymentManager action