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-llama31-204m-exp-87436-v1-mkmlizer
Waiting for job on chaiml-llama31-204m-exp-87436-v1-mkmlizer to finish
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║                                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║                                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║                                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║                                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ║                                                                     ║
chaiml-llama31-204m-exp-87436-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-204m-exp-87436-v1-mkmlizer: Downloaded to shared memory in 28.010s
chaiml-llama31-204m-exp-87436-v1-mkmlizer: Checking if ChaiML/llama31-204m-exp3-data-dynamicv1-900k-full-1e-s05-lenfilt already exists in ChaiML
chaiml-llama31-204m-exp-87436-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmprhccx5bq, device:0
chaiml-llama31-204m-exp-87436-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama31-204m-exp-87436-v1-mkmlizer: quantized model in 19.671s
chaiml-llama31-204m-exp-87436-v1-mkmlizer: Processed model ChaiML/llama31-204m-exp3-data-dynamicv1-900k-full-1e-s05-lenfilt in 47.682s
chaiml-llama31-204m-exp-87436-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-204m-exp-87436-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-204m-exp-87436-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1
chaiml-llama31-204m-exp-87436-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1/config.json
chaiml-llama31-204m-exp-87436-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1/special_tokens_map.json
chaiml-llama31-204m-exp-87436-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1/tokenizer_config.json
chaiml-llama31-204m-exp-87436-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1/tokenizer.json
chaiml-llama31-204m-exp-87436-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-204m-exp-87436-v1/flywheel_model.0.safetensors
chaiml-llama31-204m-exp-87436-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.23it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 53.83it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 45.49it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 44.36it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 50.89it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.45it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.23it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 50.65it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 47.00it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 44.58it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 49.18it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 45.95it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 44.46it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 30.19it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.07it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 36.59it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:04, 39.13it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 41.72it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 41.05it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 41.56it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.99it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 44.50it/s]
Loading 0:  45%|████▌     | 132/291 [00:03<00:03, 44.26it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 49.28it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 45.26it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 44.83it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 49.93it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 45.88it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 44.65it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 53.11it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 44.74it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 31.89it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.94it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:02, 32.32it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 37.73it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 40.03it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 41.55it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 40.44it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 40.96it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 46.86it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:01, 46.95it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 38.07it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 46.54it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 43.48it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 41.41it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 46.42it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 43.84it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 42.90it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 39.75it/s]
Loading 0:  99%|█████████▊| 287/291 [00:06<00:00, 30.21it/s]
                                                            
Job chaiml-llama31-204m-exp-87436-v1-mkmlizer completed after 74.72s with status: succeeded
Stopping job with name chaiml-llama31-204m-exp-87436-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.21s
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-llama31-204m-exp-87436-v1
Waiting for inference service chaiml-llama31-204m-exp-87436-v1 to be ready
Inference service chaiml-llama31-204m-exp-87436-v1 ready after 211.89538836479187s
Pipeline stage MKMLDeployer completed in 212.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.9894280433654785s
Received healthy response to inference request in 3.4836230278015137s
Received healthy response to inference request in 4.023099184036255s
Received healthy response to inference request in 4.6784348487854s
Received healthy response to inference request in 3.0012550354003906s
5 requests
0 failed requests
5th percentile: 3.097728633880615
10th percentile: 3.1942022323608397
20th percentile: 3.387149429321289
30th percentile: 3.591518259048462
40th percentile: 3.807308721542358
50th percentile: 4.023099184036255
60th percentile: 4.285233449935913
70th percentile: 4.547367715835571
80th percentile: 4.740633487701416
90th percentile: 4.865030765533447
95th percentile: 4.927229404449463
99th percentile: 4.976988315582275
mean time: 4.035168027877807
Pipeline stage StressChecker completed in 21.49s
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 0.67s
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 0.65s
Shutdown handler de-registered
chaiml-llama31-204m-exp_87436_v1 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 0.11s
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-llama31-204m-exp-87436-v1-profiler
Waiting for inference service chaiml-llama31-204m-exp-87436-v1-profiler to be ready
Inference service chaiml-llama31-204m-exp-87436-v1-profiler ready after 212.30329775810242s
Pipeline stage MKMLProfilerDeployer completed in 213.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw:/code/chaiverse_profiler_1751412625 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751412625 && 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_1751412625/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw:/code/chaiverse_profiler_1751413031 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751413031 && 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_1751413031/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw:/code/chaiverse_profiler_1751413441 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplomfchw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751413441 && 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_1751413441/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<00:56,  3.54it/s]\n  1%|          | 2/200 [00:03<07:01,  2.13s/it]\n  2%|▏         | 3/200 [00:07<08:49,  2.69s/it]\n  2%|▏         | 4/200 [00:07<05:39,  1.73s/it]\n  2%|▎         | 5/200 [00:10<07:29,  2.31s/it]\n  3%|▎         | 6/200 [00:13<08:35,  2.66s/it]\n  4%|▎         | 7/200 [00:17<09:14,  2.87s/it]\n  4%|▍         | 8/200 [00:20<09:39,  3.02s/it]\n  4%|▍         | 9/200 [00:24<09:58,  3.13s/it]\n  5%|▌         | 10/200 [00:24<06:58,  2.20s/it]\n  6%|▌         | 11/200 [00:24<05:04,  1.61s/it]\n  6%|▌         | 12/200 [00:27<06:42,  2.14s/it]\n  6%|▋         | 13/200 [00:28<04:53,  1.57s/it]\n  7%|▋         | 14/200 [00:28<03:38,  1.18s/it]\n  8%|▊         | 15/200 [00:31<05:38,  1.83s/it]\n  8%|▊         | 16/200 [00:31<04:09,  1.36s/it]\n  8%|▊         | 17/200 [00:35<06:01,  1.98s/it]\n  9%|▉         | 18/200 [00:35<04:25,  1.46s/it]\n 10%|▉         | 19/200 [00:38<06:07,  2.03s/it]\n 10%|█         | 20/200 [00:39<04:30,  1.50s/it]\n 10%|█         | 21/200 [00:39<03:23,  1.14s/it]\n 11%|█         | 22/200 [00:42<05:19,  1.80s/it]\n 12%|█▏        | 23/200 [00:46<06:43,  2.28s/it]\n 12%|█▏        | 24/200 [00:46<04:55,  1.68s/it]\n 12%|█▎        | 25/200 [00:49<06:23,  2.19s/it]\n 13%|█▎        | 26/200 [00:53<07:19,  2.53s/it]\n 14%|█▎        | 27/200 [00:56<07:58,  2.77s/it]\n 14%|█▍        | 28/200 [00:59<08:24,  2.93s/it]\n 14%|█▍        | 29/200 [01:03<08:42,  3.06s/it]\n 15%|█▌        | 30/200 [01:06<08:52,  3.13s/it]\n 16%|█▌        | 31/200 [01:06<06:16,  2.23s/it]\n 16%|█▌        | 32/200 [01:10<07:16,  2.60s/it]\n 16%|█▋        | 33/200 [01:13<07:49,  2.81s/it]\n 17%|█▋        | 34/200 [01:13<05:33,  2.01s/it]\n 18%|█▊        | 35/200 [01:13<04:05,  1.49s/it]\n 18%|█▊        | 36/200 [01:14<03:04,  1.12s/it]\n 18%|█▊        | 37/200 [01:14<02:22,  1.14it/s]\n 19%|█▉        | 38/200 [01:14<01:52,  1.44it/s]\n 20%|█▉        | 39/200 [01:14<01:32,  1.74it/s]\n 20%|██        | 40/200 [01:18<03:45,  1.41s/it]\n 20%|██        | 41/200 [01:18<02:49,  1.06s/it]\n 21%|██        | 42/200 [01:21<04:38,  1.76s/it]\n 22%|██▏       | 43/200 [01:25<05:53,  2.25s/it]\n 22%|██▏       | 44/200 [01:25<04:12,  1.62s/it]\n 22%|██▎       | 45/200 [01:25<03:08,  1.21s/it]\n 23%|██▎       | 46/200 [01:29<04:45,  1.86s/it]\n 24%|██▎       | 47/200 [01:32<05:52,  2.30s/it]\n 24%|██▍       | 48/200 [01:35<06:36,  2.61s/it]\n 24%|██▍       | 49/200 [01:36<04:46,  1.90s/it]\n 25%|██▌       | 50/200 [01:39<05:55,  2.37s/it]\n 26%|██▌       | 51/200 [01:42<06:36,  2.66s/it]\n 26%|██▌       | 52/200 [01:46<07:04,  2.87s/it]\n 26%|██▋       | 53/200 [01:46<05:00,  2.05s/it]\n 27%|██▋       | 54/200 [01:49<05:54,  2.43s/it]\n 28%|██▊       | 55/200 [01:52<06:30,  2.69s/it]\n 28%|██▊       | 56/200 [01:53<04:42,  1.96s/it]\n 28%|██▊       | 57/200 [01:53<03:28,  1.46s/it]\n 29%|██▉       | 58/200 [01:53<02:37,  1.11s/it]\n 30%|██▉       | 59/200 [01:54<02:00,  1.17it/s]\n 30%|███       | 60/200 [01:57<03:44,  1.60s/it]\n 30%|███       | 61/200 [01:57<02:47,  1.21s/it]\n 31%|███       | 62/200 [01:57<02:08,  1.08it/s]\n 32%|███▏      | 63/200 [01:58<01:40,  1.36it/s]\n 32%|███▏      | 64/200 [01:58<01:22,  1.66it/s]\n 32%|███▎      | 65/200 [01:58<01:09,  1.94it/s]\n 33%|███▎      | 66/200 [02:02<03:02,  1.36s/it]\n 34%|███▎      | 67/200 [02:05<04:19,  1.95s/it]\n 34%|███▍      | 68/200 [02:08<05:12,  2.37s/it]\n 34%|███▍      | 69/200 [02:12<05:44,  2.63s/it]\n 35%|███▌      | 70/200 [02:12<04:08,  1.91s/it]\n 36%|███▌      | 71/200 [02:15<05:09,  2.40s/it]\n 36%|███▌      | 72/200 [02:15<03:39,  1.71s/it]\n 36%|███▋      | 73/200 [02:19<04:40,  2.21s/it]\n 37%|███▋      | 74/200 [02:19<03:24,  1.62s/it]\n 38%|███▊      | 75/200 [02:19<02:32,  1.22s/it]\n 38%|███▊      | 76/200 [02:23<03:49,  1.85s/it]\n 38%|███▊      | 77/200 [02:26<04:48,  2.35s/it]\n 39%|███▉      | 78/200 [02:30<05:22,  2.65s/it]\n 40%|███▉      | 79/200 [02:33<05:44,  2.85s/it]\n 40%|████      | 80/200 [02:33<04:03,  2.03s/it]\n 40%|████      | 81/200 [02:33<02:59,  1.51s/it]\n 41%|████      | 82/200 [02:34<02:14,  1.14s/it]\n 42%|████▏     | 83/200 [02:37<03:28,  1.79s/it]\n 42%|████▏     | 84/200 [02:37<02:33,  1.33s/it]\n 42%|████▎     | 85/200 [02:40<03:42,  1.94s/it]\n 43%|████▎     | 86/200 [02:41<02:43,  1.43s/it]\n 44%|████▎     | 87/200 [02:44<03:45,  2.00s/it]\n 44%|████▍     | 88/200 [02:44<02:45,  1.48s/it]\n 44%|████▍     | 89/200 [02:48<03:45,  2.03s/it]\n 45%|████▌     | 90/200 [02:51<04:25,  2.42s/it]\n 46%|████▌     | 91/200 [02:51<03:13,  1.77s/it]\n 46%|████▌     | 92/200 [02:55<04:02,  2.25s/it]\n 46%|████▋     | 93/200 [02:58<04:36,  2.58s/it]\n 47%|████▋     | 94/200 [02:58<03:15,  1.85s/it]\n 48%|████▊     | 95/200 [02:58<02:24,  1.37s/it]\n 48%|████▊     | 96/200 [02:59<01:48,  1.04s/it]\n 48%|████▊     | 97/200 [02:59<01:23,  1.24it/s]\n 49%|████▉     | 98/200 [02:59<01:05,  1.56it/s]\n 50%|████▉     | 99/200 [02:59<00:53,  1.87it/s]\n 50%|█████     | 100/200 [03:03<02:15,  1.36s/it]\n 50%|█████     | 101/200 [03:06<03:11,  1.94s/it]\n 51%|█████     | 102/200 [03:09<03:50,  2.35s/it]\n 52%|█████▏    | 103/200 [03:13<04:17,  2.65s/it]\n 52%|█████▏    | 104/200 [03:16<04:32,  2.84s/it]\n 52%|█████▎    | 105/200 [03:19<04:42,  2.97s/it]\n 53%|█████▎    | 106/200 [03:22<04:48,  3.07s/it]\n 54%|█████▎    | 107/200 [03:23<03:27,  2.23s/it]\n 54%|█████▍    | 108/200 [03:23<02:30,  1.64s/it]\n 55%|█████▍    | 109/200 [03:23<01:51,  1.23s/it]\n 55%|█████▌    | 110/200 [03:24<01:24,  1.06it/s]\n 56%|█████▌    | 111/200 [03:27<02:28,  1.67s/it]\n 56%|█████▌    | 112/200 [03:30<03:09,  2.16s/it]\n 56%|█████▋    | 113/200 [03:30<02:18,  1.59s/it]\n 57%|█████▋    | 114/200 [03:31<01:43,  1.20s/it]\n 57%|█████▊    | 115/200 [03:34<02:37,  1.85s/it]\n 58%|█████▊    | 116/200 [03:37<03:12,  2.29s/it]\n 58%|█████▊    | 117/200 [03:38<02:16,  1.64s/it]\n 59%|█████▉    | 118/200 [03:38<01:40,  1.23s/it]\n 60%|█████▉    | 119/200 [03:41<02:33,  1.90s/it]\n 60%|██████    | 120/200 [03:45<03:08,  2.35s/it]\n 60%|██████    | 121/200 [03:48<03:29,  2.65s/it]\n 61%|██████    | 122/200 [03:48<02:27,  1.89s/it]\n 62%|██████▏   | 123/200 [03:52<02:59,  2.33s/it]\n 62%|██████▏   | 124/200 [03:52<02:09,  1.71s/it]\n 62%|██████▎   | 125/200 [03:55<02:43,  2.18s/it]\n 63%|██████▎   | 126/200 [03:59<03:10,  2.57s/it]\n 64%|██████▎   | 127/200 [03:59<02:14,  1.84s/it]\n 64%|██████▍   | 128/200 [04:02<02:47,  2.33s/it]\n 64%|██████▍   | 129/200 [04:05<03:06,  2.63s/it]\n 65%|██████▌   | 130/200 [04:09<03:16,  2.80s/it]\n 66%|██████▌   | 131/200 [04:12<03:28,  3.02s/it]\n 66%|██████▌   | 132/200 [04:12<02:26,  2.15s/it]\n 66%|██████▋   | 133/200 [04:13<01:46,  1.59s/it]\n 67%|██████▋   | 134/200 [04:16<02:19,  2.11s/it]\n 68%|██████▊   | 135/200 [04:16<01:40,  1.55s/it]\n 68%|██████▊   | 136/200 [04:20<02:13,  2.09s/it]\n 68%|██████▊   | 137/200 [04:20<01:37,  1.55s/it]\n 69%|██████▉   | 138/200 [04:20<01:12,  1.17s/it]\n 70%|██████▉   | 139/200 [04:23<01:50,  1.81s/it]\n 70%|███████   | 140/200 [04:27<02:15,  2.26s/it]\n 70%|███████   | 141/200 [04:30<02:31,  2.57s/it]\n 71%|███████   | 142/200 [04:33<02:42,  2.81s/it]\n 72%|███████▏  | 143/200 [04:37<02:48,  2.95s/it]\n 72%|███████▏  | 144/200 [04:37<02:00,  2.14s/it]\n 72%|███████▎  | 145/200 [04:40<02:17,  2.51s/it]\n 73%|███████▎  | 146/200 [04:44<02:29,  2.77s/it]\n 74%|███████▎  | 147/200 [04:47<02:34,  2.91s/it]\n 74%|███████▍  | 148/200 [04:50<02:36,  3.02s/it]\n 74%|███████▍  | 149/200 [04:50<01:51,  2.19s/it]\n 75%|███████▌  | 150/200 [04:54<02:06,  2.53s/it]\n 76%|███████▌  | 151/200 [04:57<02:15,  2.76s/it]\n 76%|███████▌  | 152/200 [05:01<02:24,  3.00s/it]\n 76%|███████▋  | 153/200 [05:01<01:40,  2.14s/it]\n 77%|███████▋  | 154/200 [05:01<01:12,  1.58s/it]\n 78%|███████▊  | 155/200 [05:04<01:35,  2.13s/it]\n 78%|███████▊  | 156/200 [05:08<01:50,  2.52s/it]\n 78%|███████▊  | 157/200 [05:11<01:59,  2.77s/it]\n 79%|███████▉  | 158/200 [05:11<01:22,  1.97s/it]\n 80%|███████▉  | 159/200 [05:15<01:38,  2.40s/it]\n 80%|████████  | 160/200 [05:15<01:10,  1.76s/it]\n 80%|████████  | 161/200 [05:18<01:28,  2.28s/it]\n 81%|████████  | 162/200 [05:22<01:39,  2.61s/it]\n 82%|████████▏ | 163/200 [05:25<01:42,  2.77s/it]\n 82%|████████▏ | 164/200 [05:25<01:12,  2.01s/it]\n 82%|████████▎ | 165/200 [05:26<00:52,  1.49s/it]\n 83%|████████▎ | 166/200 [05:26<00:38,  1.12s/it]\n 84%|████████▎ | 167/200 [05:26<00:28,  1.15it/s]\n 84%|████████▍ | 168/200 [05:29<00:52,  1.63s/it]\n 84%|████████▍ | 169/200 [05:30<00:37,  1.22s/it]\n 85%|████████▌ | 170/200 [05:30<00:27,  1.08it/s]\n 86%|████████▌ | 171/200 [05:30<00:21,  1.37it/s]\n 86%|████████▌ | 172/200 [05:34<00:43,  1.54s/it]\n 86%|████████▋ | 173/200 [05:37<00:56,  2.11s/it]\n 87%|████████▋ | 174/200 [05:37<00:40,  1.58s/it]\n 88%|████████▊ | 175/200 [05:41<00:52,  2.10s/it]\n 88%|████████▊ | 176/200 [05:44<00:59,  2.49s/it]\n 88%|████████▊ | 177/200 [05:47<01:02,  2.73s/it]\n 89%|████████▉ | 178/200 [05:51<01:04,  2.93s/it]\n 90%|████████▉ | 179/200 [05:54<01:04,  3.05s/it]\n 90%|█████████ | 180/200 [05:54<00:43,  2.18s/it]\n 90%|█████████ | 181/200 [05:58<00:49,  2.59s/it]\n 91%|█████████ | 182/200 [06:01<00:50,  2.81s/it]\n 92%|█████████▏| 183/200 [06:05<00:50,  2.96s/it]\n 92%|█████████▏| 184/200 [06:08<00:49,  3.07s/it]\n 92%|█████████▎| 185/200 [06:08<00:32,  2.18s/it]\n 93%|█████████▎| 186/200 [06:11<00:35,  2.53s/it]\n 94%|█████████▎| 187/200 [06:15<00:37,  2.85s/it]\n 94%|█████████▍| 188/200 [06:18<00:36,  3.04s/it]\n 94%|█████████▍| 189/200 [06:19<00:23,  2.16s/it]\n 95%|█████████▌| 190/200 [06:19<00:15,  1.60s/it]\n 96%|█████████▌| 191/200 [06:22<00:19,  2.13s/it]\n 96%|█████████▌| 192/200 [06:22<00:12,  1.56s/it]\n 96%|█████████▋| 193/200 [06:26<00:15,  2.17s/it]\n 97%|█████████▋| 194/200 [06:26<00:09,  1.57s/it]\n 98%|█████████▊| 195/200 [06:26<00:05,  1.18s/it]\n 98%|█████████▊| 196/200 [06:27<00:03,  1.10it/s]\n 98%|█████████▊| 197/200 [06:27<00:02,  1.39it/s]\n 99%|█████████▉| 198/200 [06:27<00:01,  1.70it/s]\n100%|█████████▉| 199/200 [06:31<00:01,  1.41s/it]\n100%|██████████| 200/200 [06:34<00:00,  2.00s/it]\n100%|██████████| 200/200 [06:34<00:00,  1.97s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751413441/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_1751413441/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_1751413441/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_1751413441/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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : 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 (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 : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 394.470103263855\nerrors 89\nmean length: 1.665\n\nthroughput (request / second): 0.5070092723002206\nthroughput (character / second): 0.8441704383798674\naverage request duration (s) 1.9722361612319945\n50%ile request duration (s) 3.2917224168777466\n75%ile request duration (s) 3.3479525446891785\n90%ile request duration (s) 3.407181406021118\n95%ile request duration (s) 3.468785083293915\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-llama31-204m-exp-87436-v1-profiler is running
Tearing down inference service chaiml-llama31-204m-exp-87436-v1-profiler
Service chaiml-llama31-204m-exp-87436-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.34s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama31-204m-exp-87436-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama31-204m-exp-87436-v1-profiler
Waiting for inference service chaiml-llama31-204m-exp-87436-v1-profiler to be ready
Inference service chaiml-llama31-204m-exp-87436-v1-profiler ready after 80.97389030456543s
Pipeline stage MKMLProfilerDeployer completed in 81.55s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546:/code/chaiverse_profiler_1751413985 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751413985 && 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_1751413985/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546:/code/chaiverse_profiler_1751414443 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751414443 && 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_1751414443/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546:/code/chaiverse_profiler_1751414900 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deplo7k546 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751414900 && 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_1751414900/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<00:47,  4.23it/s]\n  1%|          | 2/200 [00:00<00:48,  4.10it/s]\n  2%|▏         | 3/200 [00:00<00:51,  3.86it/s]\n  2%|▏         | 4/200 [00:01<00:49,  3.92it/s]\n  2%|▎         | 5/200 [00:04<04:31,  1.39s/it]\n  3%|▎         | 6/200 [00:04<03:14,  1.00s/it]\n  4%|▎         | 7/200 [00:08<05:50,  1.82s/it]\n  4%|▍         | 8/200 [00:11<07:30,  2.35s/it]\n  4%|▍         | 9/200 [00:15<08:34,  2.69s/it]\n  5%|▌         | 10/200 [00:18<09:16,  2.93s/it]\n  6%|▌         | 11/200 [00:18<06:39,  2.11s/it]\n  6%|▌         | 12/200 [00:18<04:43,  1.51s/it]\n  6%|▋         | 13/200 [00:22<06:32,  2.10s/it]\n  7%|▋         | 14/200 [00:22<04:45,  1.53s/it]\n  8%|▊         | 15/200 [00:26<06:35,  2.14s/it]\n  8%|▊         | 16/200 [00:29<07:45,  2.53s/it]\n  8%|▊         | 17/200 [00:33<08:34,  2.81s/it]\n  9%|▉         | 18/200 [00:33<06:04,  2.00s/it]\n 10%|▉         | 19/200 [00:33<04:27,  1.48s/it]\n 10%|█         | 20/200 [00:37<06:21,  2.12s/it]\n 10%|█         | 21/200 [00:40<07:29,  2.51s/it]\n 11%|█         | 22/200 [00:40<05:19,  1.79s/it]\n 12%|█▏        | 23/200 [00:40<03:57,  1.34s/it]\n 12%|█▏        | 24/200 [00:41<02:58,  1.01s/it]\n 12%|█▎        | 25/200 [00:41<02:18,  1.27it/s]\n 13%|█▎        | 26/200 [00:44<04:41,  1.62s/it]\n 14%|█▎        | 27/200 [00:48<06:21,  2.20s/it]\n 14%|█▍        | 28/200 [00:51<07:18,  2.55s/it]\n 14%|█▍        | 29/200 [00:55<08:04,  2.83s/it]\n 15%|█▌        | 30/200 [00:55<05:49,  2.06s/it]\n 16%|█▌        | 31/200 [00:55<04:16,  1.52s/it]\n 16%|█▌        | 32/200 [00:59<05:56,  2.12s/it]\n 16%|█▋        | 33/200 [00:59<04:14,  1.52s/it]\n 17%|█▋        | 34/200 [01:02<05:47,  2.09s/it]\n 18%|█▊        | 35/200 [01:03<04:14,  1.54s/it]\n 18%|█▊        | 36/200 [01:06<05:55,  2.16s/it]\n 18%|█▊        | 37/200 [01:06<04:13,  1.55s/it]\n 19%|█▉        | 38/200 [01:10<05:50,  2.17s/it]\n 20%|█▉        | 39/200 [01:10<04:10,  1.56s/it]\n 20%|██        | 40/200 [01:14<05:39,  2.12s/it]\n 20%|██        | 41/200 [01:17<06:50,  2.58s/it]\n 21%|██        | 42/200 [01:21<07:28,  2.84s/it]\n 22%|██▏       | 43/200 [01:21<05:18,  2.03s/it]\n 22%|██▏       | 44/200 [01:25<06:32,  2.52s/it]\n 22%|██▎       | 45/200 [01:25<04:39,  1.80s/it]\n 23%|██▎       | 46/200 [01:28<06:03,  2.36s/it]\n 24%|██▎       | 47/200 [01:32<06:51,  2.69s/it]\n 24%|██▍       | 48/200 [01:32<04:51,  1.92s/it]\n 24%|██▍       | 49/200 [01:35<06:03,  2.41s/it]\n 25%|██▌       | 50/200 [01:39<06:52,  2.75s/it]\n 26%|██▌       | 51/200 [01:39<04:52,  1.96s/it]\n 26%|██▌       | 52/200 [01:39<03:34,  1.45s/it]\n 26%|██▋       | 53/200 [01:43<05:03,  2.06s/it]\n 27%|██▋       | 54/200 [01:46<06:00,  2.47s/it]\n 28%|██▊       | 55/200 [01:50<06:39,  2.76s/it]\n 28%|██▊       | 56/200 [01:50<04:47,  2.00s/it]\n 28%|██▊       | 57/200 [01:50<03:30,  1.48s/it]\n 29%|██▉       | 58/200 [01:54<04:52,  2.06s/it]\n 30%|██▉       | 59/200 [01:54<03:33,  1.51s/it]\n 30%|███       | 60/200 [01:54<02:38,  1.13s/it]\n 30%|███       | 61/200 [01:58<04:13,  1.82s/it]\n 31%|███       | 62/200 [02:01<05:19,  2.31s/it]\n 32%|███▏      | 63/200 [02:01<03:51,  1.69s/it]\n 32%|███▏      | 64/200 [02:05<05:02,  2.22s/it]\n 32%|███▎      | 65/200 [02:05<03:39,  1.63s/it]\n 33%|███▎      | 66/200 [02:08<04:50,  2.17s/it]\n 34%|███▎      | 67/200 [02:12<05:39,  2.55s/it]\n 34%|███▍      | 68/200 [02:12<04:05,  1.86s/it]\n 34%|███▍      | 69/200 [02:16<05:07,  2.35s/it]\n 35%|███▌      | 70/200 [02:19<05:47,  2.68s/it]\n 36%|███▌      | 71/200 [02:22<06:13,  2.90s/it]\n 36%|███▌      | 72/200 [02:26<06:32,  3.07s/it]\n 36%|███▋      | 73/200 [02:26<04:42,  2.22s/it]\n 37%|███▋      | 74/200 [02:26<03:25,  1.63s/it]\n 38%|███▊      | 75/200 [02:30<04:33,  2.19s/it]\n 38%|███▊      | 76/200 [02:30<03:18,  1.60s/it]\n 38%|███▊      | 77/200 [02:34<04:30,  2.20s/it]\n 39%|███▉      | 78/200 [02:34<03:17,  1.62s/it]\n 40%|███▉      | 79/200 [02:37<04:21,  2.16s/it]\n 40%|████      | 80/200 [02:38<03:10,  1.59s/it]\n 40%|████      | 81/200 [02:41<04:14,  2.14s/it]\n 41%|████      | 82/200 [02:44<04:58,  2.53s/it]\n 42%|████▏     | 83/200 [02:48<05:31,  2.83s/it]\n 42%|████▏     | 84/200 [02:52<05:50,  3.02s/it]\n 42%|████▎     | 85/200 [02:55<06:03,  3.16s/it]\n 43%|████▎     | 86/200 [02:58<06:08,  3.23s/it]\n 44%|████▎     | 87/200 [03:02<06:10,  3.28s/it]\n 44%|████▍     | 88/200 [03:05<06:12,  3.32s/it]\n 44%|████▍     | 89/200 [03:05<04:26,  2.40s/it]\n 45%|████▌     | 90/200 [03:09<05:01,  2.74s/it]\n 46%|████▌     | 91/200 [03:09<03:32,  1.95s/it]\n 46%|████▌     | 92/200 [03:09<02:36,  1.45s/it]\n 46%|████▋     | 93/200 [03:13<03:39,  2.05s/it]\n 47%|████▋     | 94/200 [03:16<04:22,  2.48s/it]\n 48%|████▊     | 95/200 [03:17<03:09,  1.81s/it]\n 48%|████▊     | 96/200 [03:20<03:58,  2.29s/it]\n 48%|████▊     | 97/200 [03:20<02:52,  1.68s/it]\n 49%|████▉     | 98/200 [03:24<03:44,  2.20s/it]\n 50%|████▉     | 99/200 [03:27<04:20,  2.58s/it]\n 50%|█████     | 100/200 [03:30<04:43,  2.83s/it]\n 50%|█████     | 101/200 [03:31<03:23,  2.06s/it]\n 51%|█████     | 102/200 [03:34<04:03,  2.48s/it]\n 52%|█████▏    | 103/200 [03:38<04:34,  2.83s/it]\n 52%|█████▏    | 104/200 [03:38<03:13,  2.02s/it]\n 52%|█████▎    | 105/200 [03:38<02:21,  1.49s/it]\n 53%|█████▎    | 106/200 [03:38<01:44,  1.12s/it]\n 54%|█████▎    | 107/200 [03:39<01:19,  1.17it/s]\n 54%|█████▍    | 108/200 [03:42<02:30,  1.64s/it]\n 55%|█████▍    | 109/200 [03:46<03:18,  2.18s/it]\n 55%|█████▌    | 110/200 [03:46<02:23,  1.60s/it]\n 56%|█████▌    | 111/200 [03:49<03:12,  2.16s/it]\n 56%|█████▌    | 112/200 [03:53<03:43,  2.54s/it]\n 56%|█████▋    | 113/200 [03:56<04:07,  2.84s/it]\n 57%|█████▋    | 114/200 [03:57<02:57,  2.07s/it]\n 57%|█████▊    | 115/200 [04:00<03:30,  2.48s/it]\n 58%|█████▊    | 116/200 [04:03<03:52,  2.77s/it]\n 58%|█████▊    | 117/200 [04:07<04:06,  2.97s/it]\n 59%|█████▉    | 118/200 [04:10<04:17,  3.14s/it]\n 60%|█████▉    | 119/200 [04:14<04:20,  3.22s/it]\n 60%|██████    | 120/200 [04:17<04:25,  3.32s/it]\n 60%|██████    | 121/200 [04:21<04:24,  3.35s/it]\n 61%|██████    | 122/200 [04:24<04:25,  3.41s/it]\n 62%|██████▏   | 123/200 [04:28<04:24,  3.44s/it]\n 62%|██████▏   | 124/200 [04:31<04:19,  3.41s/it]\n 62%|██████▎   | 125/200 [04:31<03:01,  2.42s/it]\n 63%|██████▎   | 126/200 [04:32<02:11,  1.77s/it]\n 64%|██████▎   | 127/200 [04:35<02:45,  2.27s/it]\n 64%|██████▍   | 128/200 [04:35<01:59,  1.66s/it]\n 64%|██████▍   | 129/200 [04:39<02:35,  2.19s/it]\n 65%|██████▌   | 130/200 [04:39<01:52,  1.61s/it]\n 66%|██████▌   | 131/200 [04:42<02:29,  2.16s/it]\n 66%|██████▌   | 132/200 [04:46<02:53,  2.56s/it]\n 66%|██████▋   | 133/200 [04:46<02:04,  1.86s/it]\n 67%|██████▋   | 134/200 [04:50<02:34,  2.33s/it]\n 68%|██████▊   | 135/200 [04:50<01:50,  1.70s/it]\n 68%|██████▊   | 136/200 [04:53<02:22,  2.23s/it]\n 68%|██████▊   | 137/200 [04:53<01:42,  1.63s/it]\n 69%|██████▉   | 138/200 [04:54<01:15,  1.22s/it]\n 70%|██████▉   | 139/200 [04:54<00:56,  1.07it/s]\n 70%|███████   | 140/200 [04:54<00:43,  1.38it/s]\n 70%|███████   | 141/200 [04:55<00:34,  1.70it/s]\n 71%|███████   | 142/200 [04:58<01:23,  1.44s/it]\n 72%|███████▏  | 143/200 [05:01<01:56,  2.04s/it]\n 72%|███████▏  | 144/200 [05:02<01:22,  1.47s/it]\n 72%|███████▎  | 145/200 [05:02<01:00,  1.11s/it]\n 73%|███████▎  | 146/200 [05:02<00:45,  1.18it/s]\n 74%|███████▎  | 147/200 [05:05<01:25,  1.62s/it]\n 74%|███████▍  | 148/200 [05:09<01:54,  2.20s/it]\n 74%|███████▍  | 149/200 [05:09<01:20,  1.58s/it]\n 75%|███████▌  | 150/200 [05:09<00:59,  1.18s/it]\n 76%|███████▌  | 151/200 [05:10<00:44,  1.11it/s]\n 76%|███████▌  | 152/200 [05:13<01:19,  1.66s/it]\n 76%|███████▋  | 153/200 [05:17<01:43,  2.20s/it]\n 77%|███████▋  | 154/200 [05:20<01:58,  2.57s/it]\n 78%|███████▊  | 155/200 [05:20<01:24,  1.87s/it]\n 78%|███████▊  | 156/200 [05:24<01:46,  2.43s/it]\n 78%|███████▊  | 157/200 [05:24<01:14,  1.74s/it]\n 79%|███████▉  | 158/200 [05:28<01:36,  2.29s/it]\n 80%|███████▉  | 159/200 [05:28<01:07,  1.64s/it]\n 80%|████████  | 160/200 [05:28<00:48,  1.22s/it]\n 80%|████████  | 161/200 [05:28<00:36,  1.08it/s]\n 81%|████████  | 162/200 [05:28<00:27,  1.39it/s]\n 82%|████████▏ | 163/200 [05:32<00:56,  1.54s/it]\n 82%|████████▏ | 164/200 [05:35<01:16,  2.13s/it]\n 82%|████████▎ | 165/200 [05:36<00:54,  1.56s/it]\n 83%|████████▎ | 166/200 [05:39<01:11,  2.11s/it]\n 84%|████████▎ | 167/200 [05:43<01:23,  2.52s/it]\n 84%|████████▍ | 168/200 [05:46<01:29,  2.79s/it]\n 84%|████████▍ | 169/200 [05:50<01:33,  3.03s/it]\n 85%|████████▌ | 170/200 [05:53<01:34,  3.15s/it]\n 86%|████████▌ | 171/200 [05:56<01:33,  3.23s/it]\n 86%|████████▌ | 172/200 [05:57<01:04,  2.30s/it]\n 86%|████████▋ | 173/200 [06:00<01:13,  2.71s/it]\n 87%|████████▋ | 174/200 [06:00<00:50,  1.94s/it]\n 88%|████████▊ | 175/200 [06:04<01:00,  2.43s/it]\n 88%|████████▊ | 176/200 [06:04<00:41,  1.74s/it]\n 88%|████████▊ | 177/200 [06:04<00:29,  1.29s/it]\n 89%|████████▉ | 178/200 [06:08<00:42,  1.93s/it]\n 90%|████████▉ | 179/200 [06:08<00:29,  1.42s/it]\n 90%|█████████ | 180/200 [06:08<00:21,  1.07s/it]\n 90%|█████████ | 181/200 [06:12<00:34,  1.80s/it]\n 91%|█████████ | 182/200 [06:12<00:23,  1.33s/it]\n 92%|█████████▏| 183/200 [06:12<00:17,  1.01s/it]\n 92%|█████████▏| 184/200 [06:16<00:28,  1.76s/it]\n 92%|█████████▎| 185/200 [06:19<00:33,  2.25s/it]\n 93%|█████████▎| 186/200 [06:23<00:36,  2.61s/it]\n 94%|█████████▎| 187/200 [06:26<00:37,  2.88s/it]\n 94%|█████████▍| 188/200 [06:30<00:36,  3.07s/it]\n 94%|█████████▍| 189/200 [06:33<00:35,  3.18s/it]\n 95%|█████████▌| 190/200 [06:37<00:33,  3.35s/it]\n 96%|█████████▌| 191/200 [06:40<00:30,  3.38s/it]\n 96%|█████████▌| 192/200 [06:40<00:19,  2.40s/it]\n 96%|█████████▋| 193/200 [06:44<00:19,  2.79s/it]\n 97%|█████████▋| 194/200 [06:47<00:17,  2.98s/it]\n 98%|█████████▊| 195/200 [06:48<00:10,  2.12s/it]\n 98%|█████████▊| 196/200 [06:48<00:06,  1.56s/it]\n 98%|█████████▊| 197/200 [06:51<00:06,  2.14s/it]\n 99%|█████████▉| 198/200 [06:55<00:05,  2.54s/it]\n100%|█████████▉| 199/200 [06:58<00:02,  2.81s/it]\n100%|██████████| 200/200 [06:58<00:00,  2.03s/it]\n100%|██████████| 200/200 [06:58<00:00,  2.09s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751414900/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_1751414900/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_1751414900/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_1751414900/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 (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 : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 418.92038440704346\nerrors 85\nmean length: 1.725\n\nthroughput (request / second): 0.4774176847065772\nthroughput (character / second): 0.8235455061188457\naverage request duration (s) 2.094417395591736\n50%ile request duration (s) 3.420652151107788\n75%ile request duration (s) 3.4653042554855347\n90%ile request duration (s) 3.547083616256714\n95%ile request duration (s) 3.5950321435928343\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-llama31-204m-exp-87436-v1-profiler is running
Tearing down inference service chaiml-llama31-204m-exp-87436-v1-profiler
Service chaiml-llama31-204m-exp-87436-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.45s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama31-204m-exp-87436-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.78s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama31-204m-exp-87436-v1-profiler
Waiting for inference service chaiml-llama31-204m-exp-87436-v1-profiler to be ready
Inference service chaiml-llama31-204m-exp-87436-v1-profiler ready after 131.7769799232483s
Pipeline stage MKMLProfilerDeployer completed in 132.42s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v:/code/chaiverse_profiler_1751415540 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751415540 && 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_1751415540/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v:/code/chaiverse_profiler_1751415944 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751415944 && 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_1751415944/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v:/code/chaiverse_profiler_1751416361 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-204m-97ab6b742d3c4ac4e772c5122cbebd33-deploqln8v --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751416361 && 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_1751416361/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,  7.55it/s]\n  1%|          | 2/200 [00:03<07:00,  2.13s/it]\n  2%|▏         | 3/200 [00:07<08:58,  2.73s/it]\n  2%|▏         | 4/200 [00:10<09:44,  2.98s/it]\n  2%|▎         | 5/200 [00:13<10:12,  3.14s/it]\n  3%|▎         | 6/200 [00:14<06:50,  2.11s/it]\n  4%|▎         | 7/200 [00:14<04:52,  1.51s/it]\n  4%|▍         | 8/200 [00:17<06:51,  2.14s/it]\n  4%|▍         | 9/200 [00:18<04:58,  1.56s/it]\n  5%|▌         | 10/200 [00:18<03:42,  1.17s/it]\n  6%|▌         | 11/200 [00:21<05:51,  1.86s/it]\n  6%|▌         | 12/200 [00:22<04:18,  1.38s/it]\n  6%|▋         | 13/200 [00:25<06:13,  2.00s/it]\n  7%|▋         | 14/200 [00:28<07:34,  2.44s/it]\n  8%|▊         | 15/200 [00:29<05:30,  1.78s/it]\n  8%|▊         | 16/200 [00:32<07:02,  2.30s/it]\n  8%|▊         | 17/200 [00:36<08:08,  2.67s/it]\n  9%|▉         | 18/200 [00:39<08:58,  2.96s/it]\n 10%|▉         | 19/200 [00:43<09:24,  3.12s/it]\n 10%|█         | 20/200 [00:46<09:43,  3.24s/it]\n 10%|█         | 21/200 [00:47<07:01,  2.35s/it]\n 11%|█         | 22/200 [00:47<05:08,  1.73s/it]\n 12%|█▏        | 23/200 [00:47<03:49,  1.29s/it]\n 12%|█▏        | 24/200 [00:51<05:45,  1.96s/it]\n 12%|█▎        | 25/200 [00:54<07:01,  2.41s/it]\n 13%|█▎        | 26/200 [00:54<05:08,  1.77s/it]\n 14%|█▎        | 27/200 [00:58<06:38,  2.30s/it]\n 14%|█▍        | 28/200 [00:58<04:50,  1.69s/it]\n 14%|█▍        | 29/200 [01:02<06:19,  2.22s/it]\n 15%|█▌        | 30/200 [01:02<04:38,  1.64s/it]\n 16%|█▌        | 31/200 [01:06<06:11,  2.20s/it]\n 16%|█▌        | 32/200 [01:06<04:34,  1.63s/it]\n 16%|█▋        | 33/200 [01:09<06:06,  2.20s/it]\n 17%|█▋        | 34/200 [01:09<04:21,  1.57s/it]\n 18%|█▊        | 35/200 [01:13<06:07,  2.23s/it]\n 18%|█▊        | 36/200 [01:17<07:04,  2.59s/it]\n 18%|█▊        | 37/200 [01:20<07:39,  2.82s/it]\n 19%|█▉        | 38/200 [01:23<08:05,  3.00s/it]\n 20%|█▉        | 39/200 [01:27<08:30,  3.17s/it]\n 20%|██        | 40/200 [01:27<06:01,  2.26s/it]\n 20%|██        | 41/200 [01:31<06:53,  2.60s/it]\n 21%|██        | 42/200 [01:31<04:59,  1.90s/it]\n 22%|██▏       | 43/200 [01:34<06:21,  2.43s/it]\n 22%|██▏       | 44/200 [01:38<07:10,  2.76s/it]\n 22%|██▎       | 45/200 [01:38<05:05,  1.97s/it]\n 23%|██▎       | 46/200 [01:42<06:14,  2.43s/it]\n 24%|██▎       | 47/200 [01:45<07:09,  2.81s/it]\n 24%|██▍       | 48/200 [01:49<07:39,  3.02s/it]\n 24%|██▍       | 49/200 [01:52<07:58,  3.17s/it]\n 25%|██▌       | 50/200 [01:56<08:12,  3.28s/it]\n 26%|██▌       | 51/200 [01:59<08:18,  3.34s/it]\n 26%|██▌       | 52/200 [02:00<05:52,  2.38s/it]\n 26%|██▋       | 53/200 [02:00<04:18,  1.76s/it]\n 27%|██▋       | 54/200 [02:03<05:29,  2.25s/it]\n 28%|██▊       | 55/200 [02:07<06:15,  2.59s/it]\n 28%|██▊       | 56/200 [02:10<06:48,  2.84s/it]\n 28%|██▊       | 57/200 [02:10<04:57,  2.08s/it]\n 29%|██▉       | 58/200 [02:14<05:55,  2.51s/it]\n 30%|██▉       | 59/200 [02:14<04:12,  1.79s/it]\n 30%|███       | 60/200 [02:17<05:17,  2.27s/it]\n 30%|███       | 61/200 [02:21<06:09,  2.66s/it]\n 31%|███       | 62/200 [02:21<04:21,  1.90s/it]\n 32%|███▏      | 63/200 [02:24<05:24,  2.37s/it]\n 32%|███▏      | 64/200 [02:25<03:56,  1.74s/it]\n 32%|███▎      | 65/200 [02:25<02:55,  1.30s/it]\n 33%|███▎      | 66/200 [02:28<04:18,  1.93s/it]\n 34%|███▎      | 67/200 [02:32<05:22,  2.43s/it]\n 34%|███▍      | 68/200 [02:35<05:59,  2.72s/it]\n 34%|███▍      | 69/200 [02:36<04:14,  1.94s/it]\n 35%|███▌      | 70/200 [02:36<03:07,  1.44s/it]\n 36%|███▌      | 71/200 [02:36<02:19,  1.08s/it]\n 36%|███▌      | 72/200 [02:36<01:47,  1.19it/s]\n 36%|███▋      | 73/200 [02:37<01:24,  1.51it/s]\n 37%|███▋      | 74/200 [02:37<01:08,  1.83it/s]\n 38%|███▊      | 75/200 [02:37<00:58,  2.15it/s]\n 38%|███▊      | 76/200 [02:37<00:51,  2.43it/s]\n 38%|███▊      | 77/200 [02:41<02:45,  1.34s/it]\n 39%|███▉      | 78/200 [02:41<01:59,  1.02it/s]\n 40%|███▉      | 79/200 [02:41<01:33,  1.30it/s]\n 40%|████      | 80/200 [02:45<03:11,  1.60s/it]\n 40%|████      | 81/200 [02:45<02:17,  1.16s/it]\n 41%|████      | 82/200 [02:45<01:45,  1.12it/s]\n 42%|████▏     | 83/200 [02:46<01:22,  1.42it/s]\n 42%|████▏     | 84/200 [02:49<02:56,  1.52s/it]\n 42%|████▎     | 85/200 [02:52<03:59,  2.08s/it]\n 43%|████▎     | 86/200 [02:53<02:54,  1.53s/it]\n 44%|████▎     | 87/200 [02:56<04:03,  2.15s/it]\n 44%|████▍     | 88/200 [03:00<04:43,  2.53s/it]\n 44%|████▍     | 89/200 [03:00<03:20,  1.81s/it]\n 45%|████▌     | 90/200 [03:03<04:12,  2.29s/it]\n 46%|████▌     | 91/200 [03:03<03:03,  1.68s/it]\n 46%|████▌     | 92/200 [03:07<03:57,  2.20s/it]\n 46%|████▋     | 93/200 [03:10<04:40,  2.62s/it]\n 47%|████▋     | 94/200 [03:14<05:01,  2.84s/it]\n 48%|████▊     | 95/200 [03:14<03:32,  2.02s/it]\n 48%|████▊     | 96/200 [03:17<04:14,  2.45s/it]\n 48%|████▊     | 97/200 [03:18<03:03,  1.78s/it]\n 49%|████▉     | 98/200 [03:21<03:53,  2.29s/it]\n 50%|████▉     | 99/200 [03:25<04:28,  2.66s/it]\n 50%|█████     | 100/200 [03:25<03:10,  1.90s/it]\n 50%|█████     | 101/200 [03:25<02:20,  1.42s/it]\n 51%|█████     | 102/200 [03:28<03:16,  2.01s/it]\n 52%|█████▏    | 103/200 [03:32<03:57,  2.45s/it]\n 52%|█████▏    | 104/200 [03:35<04:25,  2.76s/it]\n 52%|█████▎    | 105/200 [03:36<03:07,  1.97s/it]\n 53%|█████▎    | 106/200 [03:39<03:48,  2.43s/it]\n 54%|█████▎    | 107/200 [03:42<04:12,  2.71s/it]\n 54%|█████▍    | 108/200 [03:46<04:30,  2.94s/it]\n 55%|█████▍    | 109/200 [03:46<03:10,  2.09s/it]\n 55%|█████▌    | 110/200 [03:46<02:19,  1.55s/it]\n 56%|█████▌    | 111/200 [03:47<01:44,  1.17s/it]\n 56%|█████▌    | 112/200 [03:50<02:42,  1.85s/it]\n 56%|█████▋    | 113/200 [03:53<03:24,  2.35s/it]\n 57%|█████▋    | 114/200 [03:54<02:28,  1.73s/it]\n 57%|█████▊    | 115/200 [03:57<03:11,  2.26s/it]\n 58%|█████▊    | 116/200 [04:01<03:38,  2.61s/it]\n 58%|█████▊    | 117/200 [04:04<04:02,  2.92s/it]\n 59%|█████▉    | 118/200 [04:08<04:13,  3.09s/it]\n 60%|█████▉    | 119/200 [04:11<04:19,  3.21s/it]\n 60%|██████    | 120/200 [04:15<04:22,  3.29s/it]\n 60%|██████    | 121/200 [04:18<04:22,  3.32s/it]\n 61%|██████    | 122/200 [04:22<04:22,  3.36s/it]\n 62%|██████▏   | 123/200 [04:25<04:22,  3.41s/it]\n 62%|██████▏   | 124/200 [04:29<04:18,  3.40s/it]\n 62%|██████▎   | 125/200 [04:29<03:01,  2.42s/it]\n 63%|██████▎   | 126/200 [04:32<03:24,  2.77s/it]\n 64%|██████▎   | 127/200 [04:36<03:36,  2.97s/it]\n 64%|██████▍   | 128/200 [04:39<03:44,  3.12s/it]\n 64%|██████▍   | 129/200 [04:39<02:37,  2.22s/it]\n 65%|██████▌   | 130/200 [04:43<03:04,  2.63s/it]\n 66%|██████▌   | 131/200 [04:43<02:09,  1.88s/it]\n 66%|██████▌   | 132/200 [04:43<01:35,  1.40s/it]\n 66%|██████▋   | 133/200 [04:47<02:14,  2.00s/it]\n 67%|██████▋   | 134/200 [04:47<01:37,  1.48s/it]\n 68%|██████▊   | 135/200 [04:50<02:14,  2.07s/it]\n 68%|██████▊   | 136/200 [04:54<02:40,  2.51s/it]\n 68%|██████▊   | 137/200 [04:57<02:56,  2.81s/it]\n 69%|██████▉   | 138/200 [05:01<03:07,  3.03s/it]\n 70%|██████▉   | 139/200 [05:04<03:10,  3.12s/it]\n 70%|███████   | 140/200 [05:08<03:14,  3.24s/it]\n 70%|███████   | 141/200 [05:08<02:16,  2.31s/it]\n 71%|███████   | 142/200 [05:12<02:36,  2.70s/it]\n 72%|███████▏  | 143/200 [05:12<01:50,  1.93s/it]\n 72%|███████▏  | 144/200 [05:15<02:16,  2.45s/it]\n 72%|███████▎  | 145/200 [05:19<02:32,  2.77s/it]\n 73%|███████▎  | 146/200 [05:19<01:46,  1.98s/it]\n 74%|███████▎  | 147/200 [05:19<01:17,  1.47s/it]\n 74%|███████▍  | 148/200 [05:23<01:47,  2.07s/it]\n 74%|███████▍  | 149/200 [05:23<01:17,  1.53s/it]\n 75%|███████▌  | 150/200 [05:23<00:57,  1.15s/it]\n 76%|███████▌  | 151/200 [05:24<00:43,  1.13it/s]\n 76%|███████▌  | 152/200 [05:27<01:20,  1.67s/it]\n 76%|███████▋  | 153/200 [05:30<01:43,  2.20s/it]\n 77%|███████▋  | 154/200 [05:34<01:58,  2.58s/it]\n 78%|███████▊  | 155/200 [05:34<01:24,  1.89s/it]\n 78%|███████▊  | 156/200 [05:34<01:01,  1.40s/it]\n 78%|███████▊  | 157/200 [05:35<00:45,  1.06s/it]\n 79%|███████▉  | 158/200 [05:38<01:14,  1.76s/it]\n 80%|███████▉  | 159/200 [05:42<01:33,  2.27s/it]\n 80%|████████  | 160/200 [05:42<01:06,  1.67s/it]\n 80%|████████  | 161/200 [05:45<01:26,  2.21s/it]\n 81%|████████  | 162/200 [05:49<01:38,  2.60s/it]\n 82%|████████▏ | 163/200 [05:52<01:46,  2.89s/it]\n 82%|████████▏ | 164/200 [05:56<01:51,  3.09s/it]\n 82%|████████▎ | 165/200 [05:56<01:17,  2.21s/it]\n 83%|████████▎ | 166/200 [05:56<00:55,  1.63s/it]\n 84%|████████▎ | 167/200 [05:57<00:40,  1.22s/it]\n 84%|████████▍ | 168/200 [05:57<00:30,  1.06it/s]\n 84%|████████▍ | 169/200 [05:57<00:23,  1.35it/s]\n 85%|████████▌ | 170/200 [05:58<00:18,  1.66it/s]\n 86%|████████▌ | 171/200 [06:01<00:43,  1.49s/it]\n 86%|████████▌ | 172/200 [06:05<00:59,  2.12s/it]\n 86%|████████▋ | 173/200 [06:05<00:42,  1.56s/it]\n 87%|████████▋ | 174/200 [06:05<00:30,  1.17s/it]\n 88%|████████▊ | 175/200 [06:09<00:46,  1.86s/it]\n 88%|████████▊ | 176/200 [06:12<00:56,  2.35s/it]\n 88%|████████▊ | 177/200 [06:12<00:38,  1.69s/it]\n 89%|████████▉ | 178/200 [06:16<00:49,  2.27s/it]\n 90%|████████▉ | 179/200 [06:16<00:34,  1.63s/it]\n 90%|█████████ | 180/200 [06:19<00:43,  2.17s/it]\n 90%|█████████ | 181/200 [06:23<00:49,  2.60s/it]\n 91%|█████████ | 182/200 [06:27<00:51,  2.87s/it]\n 92%|█████████▏| 183/200 [06:30<00:52,  3.07s/it]\n 92%|█████████▏| 184/200 [06:34<00:51,  3.20s/it]\n 92%|█████████▎| 185/200 [06:37<00:49,  3.30s/it]\n 93%|█████████▎| 186/200 [06:37<00:32,  2.35s/it]\n 94%|█████████▎| 187/200 [06:41<00:34,  2.67s/it]\n 94%|█████████▍| 188/200 [06:41<00:23,  1.94s/it]\n 94%|█████████▍| 189/200 [06:44<00:26,  2.42s/it]\n 95%|█████████▌| 190/200 [06:45<00:17,  1.76s/it]\n 96%|█████████▌| 191/200 [06:48<00:21,  2.34s/it]\n 96%|█████████▌| 192/200 [06:49<00:13,  1.68s/it]\n 96%|█████████▋| 193/200 [06:49<00:08,  1.26s/it]\n 97%|█████████▋| 194/200 [06:49<00:05,  1.03it/s]\n 98%|█████████▊| 195/200 [06:53<00:08,  1.75s/it]\n 98%|█████████▊| 196/200 [06:53<00:05,  1.31s/it]\n 98%|█████████▊| 197/200 [06:53<00:03,  1.00s/it]\n 99%|█████████▉| 198/200 [06:57<00:03,  1.73s/it]\n100%|█████████▉| 199/200 [07:00<00:02,  2.27s/it]\n100%|██████████| 200/200 [07:01<00:00,  1.68s/it]\n100%|██████████| 200/200 [07:01<00:00,  2.11s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751416361/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_1751416361/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_1751416361/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_1751416361/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 : 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 : 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 (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 : 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 : 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 (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 : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 421.0225465297699\nerrors 85\nmean length: 1.725\n\nthroughput (request / second): 0.4750339421213355\nthroughput (character / second): 0.8194335501593037\naverage request duration (s) 2.1050014972686766\n50%ile request duration (s) 3.4056339263916016\n75%ile request duration (s) 3.501504063606262\n90%ile request duration (s) 3.562272882461548\n95%ile request duration (s) 3.59274605512619\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-llama31-204m-exp-87436-v1-profiler is running
Tearing down inference service chaiml-llama31-204m-exp-87436-v1-profiler
Service chaiml-llama31-204m-exp-87436-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.31s
Shutdown handler de-registered
chaiml-llama31-204m-exp_87436_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama31-204m-exp_87436_v1 status is now torndown due to DeploymentManager action