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-llama-8b-nis-ft-73782-v1-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ft-73782-v1-mkmlizer to finish
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: Downloaded to shared memory in 27.387s
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: Checking if ChaiML/llama_8b_nis_ft_new1m_512seq_v6250 already exists in ChaiML
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpzmtcbgf3, device:0
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: quantized model in 19.246s
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: Processed model ChaiML/llama_8b_nis_ft_new1m_512seq_v6250 in 46.634s
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia/config.json
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia/tokenizer.json
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-ft-73782-v1/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-ft-73782-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.66it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 55.62it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 49.87it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 50.80it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 53.25it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 47.46it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 44.81it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 50.89it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 45.98it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 45.27it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 51.13it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 47.68it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:04, 46.68it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 32.20it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 31.64it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 39.20it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.62it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.38it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 46.84it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 43.31it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.34it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 48.79it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:03, 44.66it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 45.05it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 50.73it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:02, 46.10it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 45.76it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 51.50it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 48.09it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 51.37it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 51.42it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 32.05it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 33.75it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 38.36it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 39.02it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:01, 39.65it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 43.95it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 45.28it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 41.27it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.65it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 46.93it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 46.24it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 51.08it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 47.64it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 46.54it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 52.21it/s]
Loading 0:  96%|█████████▌| 280/291 [00:06<00:00, 48.15it/s]
Loading 0:  98%|█████████▊| 285/291 [00:06<00:00, 47.77it/s]
Loading 0: 100%|█████████▉| 290/291 [00:06<00:00, 34.25it/s]
                                                            
Job chaiml-llama-8b-nis-ft-73782-v1-mkmlizer completed after 75.39s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ft-73782-v1-mkmlizer
Pipeline stage MKMLizer completed in 75.88s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-ft-73782-v1
Waiting for inference service chaiml-llama-8b-nis-ft-73782-v1 to be ready
Inference service chaiml-llama-8b-nis-ft-73782-v1 ready after 210.96936774253845s
Pipeline stage MKMLDeployer completed in 211.49s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.895433187484741s
Received healthy response to inference request in 3.669816732406616s
Received healthy response to inference request in 3.151181697845459s
Received healthy response to inference request in 4.662075757980347s
5 requests
1 failed requests
5th percentile: 3.2549087047576903
10th percentile: 3.3586357116699217
20th percentile: 3.566089725494385
30th percentile: 3.7149400234222414
40th percentile: 3.8051866054534913
50th percentile: 3.895433187484741
60th percentile: 4.202090215682984
70th percentile: 4.508747243881225
80th percentile: 7.756242418289187
90th percentile: 13.944575738906861
95th percentile: 17.038742399215696
99th percentile: 19.514075727462767
mean time: 7.10228328704834
%s, retrying in %s seconds...
Received healthy response to inference request in 2.873018264770508s
Received healthy response to inference request in 3.425504207611084s
Received healthy response to inference request in 3.9225687980651855s
Received healthy response to inference request in 2.9604287147521973s
Received healthy response to inference request in 3.278032064437866s
5 requests
0 failed requests
5th percentile: 2.8905003547668455
10th percentile: 2.9079824447631837
20th percentile: 2.9429466247558596
30th percentile: 3.023949384689331
40th percentile: 3.1509907245635986
50th percentile: 3.278032064437866
60th percentile: 3.337020921707153
70th percentile: 3.3960097789764405
80th percentile: 3.5249171257019043
90th percentile: 3.723742961883545
95th percentile: 3.8231558799743652
99th percentile: 3.9026862144470216
mean time: 3.291910409927368
Pipeline stage StressChecker completed in 54.20s
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 0.69s
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 0.87s
Shutdown handler de-registered
chaiml-llama-8b-nis-ft-_73782_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 0.17s
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-llama-8b-nis-ft-73782-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-ft-73782-v1-profiler to be ready
Inference service chaiml-llama-8b-nis-ft-73782-v1-profiler ready after 222.67461490631104s
Pipeline stage MKMLProfilerDeployer completed in 223.66s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks:/code/chaiverse_profiler_1751606088 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751606088 && 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_1751606088/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks:/code/chaiverse_profiler_1751606539 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751606539 && 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_1751606539/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks:/code/chaiverse_profiler_1751606972 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deploxdzks --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751606972 && 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_1751606972/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n  0%|          | 0/200 [00:00<?, ?it/s]\n  0%|          | 1/200 [00:00<00:48,  4.08it/s]\n  1%|          | 2/200 [00:00<00:50,  3.88it/s]\n  2%|▏         | 3/200 [00:00<00:52,  3.73it/s]\n  2%|▏         | 4/200 [00:04<05:03,  1.55s/it]\n  2%|▎         | 5/200 [00:07<07:18,  2.25s/it]\n  3%|▎         | 6/200 [00:11<08:36,  2.66s/it]\n  4%|▎         | 7/200 [00:11<06:01,  1.87s/it]\n  4%|▍         | 8/200 [00:14<07:36,  2.38s/it]\n  4%|▍         | 9/200 [00:18<08:47,  2.76s/it]\n  5%|▌         | 10/200 [00:18<06:09,  1.95s/it]\n  6%|▌         | 11/200 [00:22<07:36,  2.42s/it]\n  6%|▌         | 12/200 [00:25<08:39,  2.77s/it]\n  6%|▋         | 13/200 [00:25<06:07,  1.97s/it]\n  7%|▋         | 14/200 [00:26<04:29,  1.45s/it]\n  8%|▊         | 15/200 [00:29<06:25,  2.08s/it]\n  8%|▊         | 16/200 [00:33<07:49,  2.55s/it]\n  8%|▊         | 17/200 [00:33<05:33,  1.82s/it]\n  9%|▉         | 18/200 [00:37<07:06,  2.34s/it]\n 10%|▉         | 19/200 [00:40<08:13,  2.73s/it]\n 10%|█         | 20/200 [00:40<05:50,  1.95s/it]\n 10%|█         | 21/200 [00:41<04:18,  1.44s/it]\n 11%|█         | 22/200 [00:41<03:13,  1.09s/it]\n 12%|█▏        | 23/200 [00:44<05:20,  1.81s/it]\n 12%|█▏        | 24/200 [00:48<06:49,  2.32s/it]\n 12%|█▎        | 25/200 [00:51<07:53,  2.71s/it]\n 13%|█▎        | 26/200 [00:55<08:30,  2.94s/it]\n 14%|█▎        | 27/200 [00:58<09:01,  3.13s/it]\n 14%|█▍        | 28/200 [01:02<09:24,  3.28s/it]\n 14%|█▍        | 29/200 [01:02<06:39,  2.33s/it]\n 15%|█▌        | 30/200 [01:06<07:38,  2.70s/it]\n 16%|█▌        | 31/200 [01:09<08:21,  2.97s/it]\n 16%|█▌        | 32/200 [01:09<05:55,  2.12s/it]\n 16%|█▋        | 33/200 [01:10<04:20,  1.56s/it]\n 17%|█▋        | 34/200 [01:13<05:56,  2.15s/it]\n 18%|█▊        | 35/200 [01:17<07:09,  2.60s/it]\n 18%|█▊        | 36/200 [01:17<05:04,  1.86s/it]\n 18%|█▊        | 37/200 [01:21<06:24,  2.36s/it]\n 19%|█▉        | 38/200 [01:24<07:25,  2.75s/it]\n 20%|█▉        | 39/200 [01:24<05:15,  1.96s/it]\n 20%|██        | 40/200 [01:25<03:52,  1.45s/it]\n 20%|██        | 41/200 [01:28<05:28,  2.07s/it]\n 21%|██        | 42/200 [01:28<03:59,  1.52s/it]\n 22%|██▏       | 43/200 [01:32<05:35,  2.14s/it]\n 22%|██▏       | 44/200 [01:35<06:36,  2.54s/it]\n 22%|██▎       | 45/200 [01:36<04:41,  1.82s/it]\n 23%|██▎       | 46/200 [01:39<05:58,  2.33s/it]\n 24%|██▎       | 47/200 [01:39<04:20,  1.70s/it]\n 24%|██▍       | 48/200 [01:40<03:13,  1.27s/it]\n 24%|██▍       | 49/200 [01:40<02:26,  1.03it/s]\n 25%|██▌       | 50/200 [01:40<01:54,  1.31it/s]\n 26%|██▌       | 51/200 [01:44<03:55,  1.58s/it]\n 26%|██▌       | 52/200 [01:44<02:55,  1.19s/it]\n 26%|██▋       | 53/200 [01:47<04:38,  1.89s/it]\n 27%|██▋       | 54/200 [01:51<05:45,  2.37s/it]\n 28%|██▊       | 55/200 [01:54<06:30,  2.70s/it]\n 28%|██▊       | 56/200 [01:58<07:07,  2.97s/it]\n 28%|██▊       | 57/200 [01:58<05:07,  2.15s/it]\n 29%|██▉       | 58/200 [02:02<06:02,  2.55s/it]\n 30%|██▉       | 59/200 [02:05<06:40,  2.84s/it]\n 30%|███       | 60/200 [02:09<07:04,  3.03s/it]\n 30%|███       | 61/200 [02:09<05:06,  2.21s/it]\n 31%|███       | 62/200 [02:13<06:00,  2.61s/it]\n 32%|███▏      | 63/200 [02:13<04:20,  1.90s/it]\n 32%|███▏      | 64/200 [02:16<05:24,  2.38s/it]\n 32%|███▎      | 65/200 [02:17<03:55,  1.74s/it]\n 33%|███▎      | 66/200 [02:20<05:05,  2.28s/it]\n 34%|███▎      | 67/200 [02:20<03:42,  1.67s/it]\n 34%|███▍      | 68/200 [02:24<04:54,  2.23s/it]\n 34%|███▍      | 69/200 [02:24<03:34,  1.63s/it]\n 35%|███▌      | 70/200 [02:28<04:45,  2.19s/it]\n 36%|███▌      | 71/200 [02:28<03:27,  1.61s/it]\n 36%|███▌      | 72/200 [02:31<04:38,  2.17s/it]\n 36%|███▋      | 73/200 [02:35<05:26,  2.57s/it]\n 37%|███▋      | 74/200 [02:38<05:59,  2.85s/it]\n 38%|███▊      | 75/200 [02:38<04:14,  2.03s/it]\n 38%|███▊      | 76/200 [02:42<05:14,  2.53s/it]\n 38%|███▊      | 77/200 [02:42<03:42,  1.81s/it]\n 39%|███▉      | 78/200 [02:43<02:44,  1.35s/it]\n 40%|███▉      | 79/200 [02:46<04:02,  2.00s/it]\n 40%|████      | 80/200 [02:50<04:54,  2.45s/it]\n 40%|████      | 81/200 [02:53<05:29,  2.77s/it]\n 41%|████      | 82/200 [02:53<03:57,  2.01s/it]\n 42%|████▏     | 83/200 [02:57<04:47,  2.46s/it]\n 42%|████▏     | 84/200 [02:57<03:28,  1.79s/it]\n 42%|████▎     | 85/200 [02:57<02:33,  1.34s/it]\n 43%|████▎     | 86/200 [03:01<03:47,  2.00s/it]\n 44%|████▎     | 87/200 [03:05<04:41,  2.49s/it]\n 44%|████▍     | 88/200 [03:08<05:12,  2.79s/it]\n 44%|████▍     | 89/200 [03:08<03:40,  1.99s/it]\n 45%|████▌     | 90/200 [03:08<02:42,  1.47s/it]\n 46%|████▌     | 91/200 [03:12<03:47,  2.09s/it]\n 46%|████▌     | 92/200 [03:15<04:30,  2.51s/it]\n 46%|████▋     | 93/200 [03:19<05:01,  2.82s/it]\n 47%|████▋     | 94/200 [03:19<03:36,  2.04s/it]\n 48%|████▊     | 95/200 [03:23<04:18,  2.46s/it]\n 48%|████▊     | 96/200 [03:23<03:07,  1.80s/it]\n 48%|████▊     | 97/200 [03:27<04:02,  2.36s/it]\n 49%|████▉     | 98/200 [03:27<02:52,  1.69s/it]\n 50%|████▉     | 99/200 [03:27<02:07,  1.26s/it]\n 50%|█████     | 100/200 [03:27<01:36,  1.04it/s]\n 50%|█████     | 101/200 [03:31<02:49,  1.72s/it]\n 51%|█████     | 102/200 [03:34<03:41,  2.26s/it]\n 52%|█████▏    | 103/200 [03:38<04:20,  2.68s/it]\n 52%|█████▏    | 104/200 [03:38<03:03,  1.91s/it]\n 52%|█████▎    | 105/200 [03:42<03:47,  2.40s/it]\n 53%|█████▎    | 106/200 [03:42<02:44,  1.75s/it]\n 54%|█████▎    | 107/200 [03:42<02:01,  1.31s/it]\n 54%|█████▍    | 108/200 [03:42<01:31,  1.00it/s]\n 55%|█████▍    | 109/200 [03:46<02:39,  1.75s/it]\n 55%|█████▌    | 110/200 [03:46<01:57,  1.31s/it]\n 56%|█████▌    | 111/200 [03:50<02:54,  1.97s/it]\n 56%|█████▌    | 112/200 [03:50<02:07,  1.45s/it]\n 56%|█████▋    | 113/200 [03:50<01:35,  1.10s/it]\n 57%|█████▋    | 114/200 [03:50<01:13,  1.17it/s]\n 57%|█████▊    | 115/200 [03:51<00:57,  1.47it/s]\n 58%|█████▊    | 116/200 [03:54<02:07,  1.52s/it]\n 58%|█████▊    | 117/200 [03:58<02:56,  2.13s/it]\n 59%|█████▉    | 118/200 [04:01<03:29,  2.55s/it]\n 60%|█████▉    | 119/200 [04:05<03:49,  2.83s/it]\n 60%|██████    | 120/200 [04:05<02:41,  2.02s/it]\n 60%|██████    | 121/200 [04:05<01:57,  1.49s/it]\n 61%|██████    | 122/200 [04:05<01:27,  1.12s/it]\n 62%|██████▏   | 123/200 [04:09<02:24,  1.87s/it]\n 62%|██████▏   | 124/200 [04:13<03:00,  2.37s/it]\n 62%|██████▎   | 125/200 [04:16<03:23,  2.72s/it]\n 63%|██████▎   | 126/200 [04:16<02:23,  1.94s/it]\n 64%|██████▎   | 127/200 [04:16<01:44,  1.44s/it]\n 64%|██████▍   | 128/200 [04:17<01:18,  1.08s/it]\n 64%|██████▍   | 129/200 [04:20<02:08,  1.81s/it]\n 65%|██████▌   | 130/200 [04:20<01:33,  1.34s/it]\n 66%|██████▌   | 131/200 [04:21<01:10,  1.02s/it]\n 66%|██████▌   | 132/200 [04:24<01:59,  1.76s/it]\n 66%|██████▋   | 133/200 [04:24<01:27,  1.30s/it]\n 67%|██████▋   | 134/200 [04:28<02:09,  1.97s/it]\n 68%|██████▊   | 135/200 [04:28<01:34,  1.46s/it]\n 68%|██████▊   | 136/200 [04:32<02:12,  2.07s/it]\n 68%|██████▊   | 137/200 [04:35<02:39,  2.53s/it]\n 69%|██████▉   | 138/200 [04:39<02:53,  2.79s/it]\n 70%|██████▉   | 139/200 [04:42<03:05,  3.04s/it]\n 70%|███████   | 140/200 [04:46<03:11,  3.19s/it]\n 70%|███████   | 141/200 [04:46<02:14,  2.27s/it]\n 71%|███████   | 142/200 [04:50<02:35,  2.68s/it]\n 72%|███████▏  | 143/200 [04:53<02:43,  2.88s/it]\n 72%|███████▏  | 144/200 [04:53<01:56,  2.09s/it]\n 72%|███████▎  | 145/200 [04:57<02:17,  2.51s/it]\n 73%|███████▎  | 146/200 [04:57<01:38,  1.83s/it]\n 74%|███████▎  | 147/200 [04:57<01:11,  1.35s/it]\n 74%|███████▍  | 148/200 [05:01<01:43,  2.00s/it]\n 74%|███████▍  | 149/200 [05:01<01:14,  1.47s/it]\n 75%|███████▌  | 150/200 [05:01<00:55,  1.11s/it]\n 76%|███████▌  | 151/200 [05:01<00:41,  1.17it/s]\n 76%|███████▌  | 152/200 [05:02<00:32,  1.47it/s]\n 76%|███████▋  | 153/200 [05:02<00:26,  1.79it/s]\n 77%|███████▋  | 154/200 [05:06<01:07,  1.46s/it]\n 78%|███████▊  | 155/200 [05:09<01:32,  2.06s/it]\n 78%|███████▊  | 156/200 [05:12<01:49,  2.48s/it]\n 78%|███████▊  | 157/200 [05:13<01:17,  1.81s/it]\n 79%|███████▉  | 158/200 [05:13<00:57,  1.36s/it]\n 80%|███████▉  | 159/200 [05:17<01:22,  2.01s/it]\n 80%|████████  | 160/200 [05:20<01:37,  2.44s/it]\n 80%|████████  | 161/200 [05:20<01:09,  1.79s/it]\n 81%|████████  | 162/200 [05:24<01:28,  2.33s/it]\n 82%|████████▏ | 163/200 [05:27<01:39,  2.69s/it]\n 82%|████████▏ | 164/200 [05:31<01:46,  2.95s/it]\n 82%|████████▎ | 165/200 [05:31<01:15,  2.15s/it]\n 83%|████████▎ | 166/200 [05:35<01:26,  2.53s/it]\n 84%|████████▎ | 167/200 [05:38<01:32,  2.81s/it]\n 84%|████████▍ | 168/200 [05:38<01:04,  2.01s/it]\n 84%|████████▍ | 169/200 [05:42<01:17,  2.49s/it]\n 85%|████████▌ | 170/200 [05:45<01:23,  2.79s/it]\n 86%|████████▌ | 171/200 [05:49<01:27,  3.01s/it]\n 86%|████████▌ | 172/200 [05:49<00:59,  2.14s/it]\n 86%|████████▋ | 173/200 [05:53<01:09,  2.56s/it]\n 87%|████████▋ | 174/200 [05:56<01:14,  2.86s/it]\n 88%|████████▊ | 175/200 [05:56<00:50,  2.04s/it]\n 88%|████████▊ | 176/200 [06:00<01:01,  2.55s/it]\n 88%|████████▊ | 177/200 [06:03<01:05,  2.84s/it]\n 89%|████████▉ | 178/200 [06:04<00:44,  2.02s/it]\n 90%|████████▉ | 179/200 [06:07<00:51,  2.47s/it]\n 90%|█████████ | 180/200 [06:07<00:36,  1.81s/it]\n 90%|█████████ | 181/200 [06:08<00:25,  1.35s/it]\n 91%|█████████ | 182/200 [06:11<00:36,  2.00s/it]\n 92%|█████████▏| 183/200 [06:11<00:25,  1.49s/it]\n 92%|█████████▏| 184/200 [06:12<00:17,  1.12s/it]\n 92%|█████████▎| 185/200 [06:15<00:27,  1.84s/it]\n 93%|█████████▎| 186/200 [06:19<00:33,  2.39s/it]\n 94%|█████████▎| 187/200 [06:19<00:22,  1.71s/it]\n 94%|█████████▍| 188/200 [06:23<00:27,  2.26s/it]\n 94%|█████████▍| 189/200 [06:26<00:29,  2.67s/it]\n 95%|█████████▌| 190/200 [06:26<00:19,  1.90s/it]\n 96%|█████████▌| 191/200 [06:27<00:12,  1.42s/it]\n 96%|█████████▌| 192/200 [06:30<00:16,  2.04s/it]\n 96%|█████████▋| 193/200 [06:30<00:10,  1.50s/it]\n 97%|█████████▋| 194/200 [06:34<00:12,  2.15s/it]\n 98%|█████████▊| 195/200 [06:38<00:12,  2.56s/it]\n 98%|█████████▊| 196/200 [06:41<00:11,  2.84s/it]\n 98%|█████████▊| 197/200 [06:41<00:06,  2.02s/it]\n 99%|█████████▉| 198/200 [06:45<00:05,  2.51s/it]\n100%|█████████▉| 199/200 [06:48<00:02,  2.81s/it]\n100%|██████████| 200/200 [06:48<00:00,  2.01s/it]\n100%|██████████| 200/200 [06:48<00:00,  2.04s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751606972/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_1751606972/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_1751606972/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_1751606972/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 : 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 (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : 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"}\')\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 : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : 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): 408.9479196071625\nerrors 90\nmean length: 1.65\n\nthroughput (request / second): 0.4890598298974624\nthroughput (character / second): 0.8069487193308129\naverage request duration (s) 2.0445894873142243\n50%ile request duration (s) 3.467595338821411\n75%ile request duration (s) 3.5266465544700623\n90%ile request duration (s) 3.600005340576172\n95%ile request duration (s) 3.6402644991874693\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-llama-8b-nis-ft-73782-v1-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ft-73782-v1-profiler
Service chaiml-llama-8b-nis-ft-73782-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.27s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-nis-ft-73782-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 4.05s
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-llama-8b-nis-ft-73782-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-ft-73782-v1-profiler to be ready
Inference service chaiml-llama-8b-nis-ft-73782-v1-profiler ready after 202.61853647232056s
Pipeline stage MKMLProfilerDeployer completed in 203.24s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc:/code/chaiverse_profiler_1751607651 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751607651 && 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_1751607651/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc:/code/chaiverse_profiler_1751608110 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751608110 && 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_1751608110/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc:/code/chaiverse_profiler_1751608530 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplopvkwc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751608530 && 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_1751608530/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<10:58,  3.31s/it]\n  1%|          | 2/200 [00:06<10:59,  3.33s/it]\n  2%|▏         | 3/200 [00:06<06:07,  1.86s/it]\n  2%|▏         | 4/200 [00:10<08:12,  2.51s/it]\n  2%|▎         | 5/200 [00:13<09:10,  2.83s/it]\n  3%|▎         | 6/200 [00:13<06:09,  1.91s/it]\n  4%|▎         | 7/200 [00:14<04:23,  1.36s/it]\n  4%|▍         | 8/200 [00:14<03:13,  1.01s/it]\n  4%|▍         | 9/200 [00:17<05:32,  1.74s/it]\n  5%|▌         | 10/200 [00:17<04:02,  1.28s/it]\n  6%|▌         | 11/200 [00:21<06:06,  1.94s/it]\n  6%|▌         | 12/200 [00:24<07:24,  2.36s/it]\n  6%|▋         | 13/200 [00:24<05:22,  1.73s/it]\n  7%|▋         | 14/200 [00:28<06:53,  2.22s/it]\n  8%|▊         | 15/200 [00:31<07:58,  2.59s/it]\n  8%|▊         | 16/200 [00:31<05:48,  1.89s/it]\n  8%|▊         | 17/200 [00:32<04:16,  1.40s/it]\n  9%|▉         | 18/200 [00:35<06:04,  2.00s/it]\n 10%|▉         | 19/200 [00:35<04:27,  1.48s/it]\n 10%|█         | 20/200 [00:39<06:07,  2.04s/it]\n 10%|█         | 21/200 [00:39<04:22,  1.47s/it]\n 11%|█         | 22/200 [00:42<06:04,  2.05s/it]\n 12%|█▏        | 23/200 [00:46<07:11,  2.44s/it]\n 12%|█▏        | 24/200 [00:46<05:12,  1.77s/it]\n 12%|█▎        | 25/200 [00:49<06:34,  2.25s/it]\n 13%|█▎        | 26/200 [00:53<07:37,  2.63s/it]\n 14%|█▎        | 27/200 [00:53<05:25,  1.88s/it]\n 14%|█▍        | 28/200 [00:56<06:37,  2.31s/it]\n 14%|█▍        | 29/200 [00:56<04:48,  1.69s/it]\n 15%|█▌        | 30/200 [00:57<03:33,  1.26s/it]\n 16%|█▌        | 31/200 [01:00<05:19,  1.89s/it]\n 16%|█▌        | 32/200 [01:03<06:33,  2.34s/it]\n 16%|█▋        | 33/200 [01:04<04:45,  1.71s/it]\n 17%|█▋        | 34/200 [01:07<06:11,  2.24s/it]\n 18%|█▊        | 35/200 [01:10<07:00,  2.55s/it]\n 18%|█▊        | 36/200 [01:11<05:11,  1.90s/it]\n 18%|█▊        | 37/200 [01:14<06:29,  2.39s/it]\n 19%|█▉        | 38/200 [01:14<04:37,  1.71s/it]\n 20%|█▉        | 39/200 [01:18<06:03,  2.26s/it]\n 20%|██        | 40/200 [01:18<04:19,  1.62s/it]\n 20%|██        | 41/200 [01:22<05:41,  2.15s/it]\n 21%|██        | 42/200 [01:22<04:11,  1.59s/it]\n 22%|██▏       | 43/200 [01:22<03:07,  1.20s/it]\n 22%|██▏       | 44/200 [01:25<04:49,  1.85s/it]\n 22%|██▎       | 45/200 [01:26<03:33,  1.38s/it]\n 23%|██▎       | 46/200 [01:29<05:04,  1.98s/it]\n 24%|██▎       | 47/200 [01:29<03:43,  1.46s/it]\n 24%|██▍       | 48/200 [01:33<05:22,  2.12s/it]\n 24%|██▍       | 49/200 [01:36<06:18,  2.50s/it]\n 25%|██▌       | 50/200 [01:40<06:58,  2.79s/it]\n 26%|██▌       | 51/200 [01:40<04:56,  1.99s/it]\n 26%|██▌       | 52/200 [01:43<06:01,  2.44s/it]\n 26%|██▋       | 53/200 [01:44<04:24,  1.80s/it]\n 27%|██▋       | 54/200 [01:44<03:15,  1.34s/it]\n 28%|██▊       | 55/200 [01:44<02:27,  1.02s/it]\n 28%|██▊       | 56/200 [01:45<01:53,  1.27it/s]\n 28%|██▊       | 57/200 [01:48<03:42,  1.55s/it]\n 29%|██▉       | 58/200 [01:48<02:46,  1.17s/it]\n 30%|██▉       | 59/200 [01:52<04:18,  1.83s/it]\n 30%|███       | 60/200 [01:52<03:09,  1.35s/it]\n 30%|███       | 61/200 [01:52<02:22,  1.02s/it]\n 31%|███       | 62/200 [01:55<03:59,  1.74s/it]\n 32%|███▏      | 63/200 [01:59<05:07,  2.25s/it]\n 32%|███▏      | 64/200 [01:59<03:44,  1.65s/it]\n 32%|███▎      | 65/200 [02:03<04:53,  2.17s/it]\n 33%|███▎      | 66/200 [02:06<05:41,  2.55s/it]\n 34%|███▎      | 67/200 [02:09<06:11,  2.80s/it]\n 34%|███▍      | 68/200 [02:09<04:23,  2.00s/it]\n 34%|███▍      | 69/200 [02:13<05:20,  2.45s/it]\n 35%|███▌      | 70/200 [02:13<03:47,  1.75s/it]\n 36%|███▌      | 71/200 [02:13<02:48,  1.30s/it]\n 36%|███▌      | 72/200 [02:17<04:06,  1.93s/it]\n 36%|███▋      | 73/200 [02:17<03:01,  1.43s/it]\n 37%|███▋      | 74/200 [02:17<02:15,  1.08s/it]\n 38%|███▊      | 75/200 [02:18<01:43,  1.21it/s]\n 38%|███▊      | 76/200 [02:21<03:16,  1.58s/it]\n 38%|███▊      | 77/200 [02:24<04:23,  2.14s/it]\n 39%|███▉      | 78/200 [02:28<05:03,  2.49s/it]\n 40%|███▉      | 79/200 [02:31<05:32,  2.75s/it]\n 40%|████      | 80/200 [02:34<05:52,  2.93s/it]\n 40%|████      | 81/200 [02:38<06:05,  3.07s/it]\n 41%|████      | 82/200 [02:38<04:22,  2.22s/it]\n 42%|████▏     | 83/200 [02:41<05:01,  2.57s/it]\n 42%|████▏     | 84/200 [02:45<05:26,  2.82s/it]\n 42%|████▎     | 85/200 [02:48<05:43,  2.99s/it]\n 43%|████▎     | 86/200 [02:52<05:56,  3.13s/it]\n 44%|████▎     | 87/200 [02:55<05:57,  3.17s/it]\n 44%|████▍     | 88/200 [02:58<06:06,  3.27s/it]\n 44%|████▍     | 89/200 [03:02<06:06,  3.30s/it]\n 45%|████▌     | 90/200 [03:02<04:17,  2.34s/it]\n 46%|████▌     | 91/200 [03:02<03:07,  1.72s/it]\n 46%|████▌     | 92/200 [03:05<04:00,  2.22s/it]\n 46%|████▋     | 93/200 [03:09<04:41,  2.63s/it]\n 47%|████▋     | 94/200 [03:12<05:01,  2.84s/it]\n 48%|████▊     | 95/200 [03:16<05:16,  3.01s/it]\n 48%|████▊     | 96/200 [03:16<03:42,  2.14s/it]\n 48%|████▊     | 97/200 [03:19<04:23,  2.56s/it]\n 49%|████▉     | 98/200 [03:20<03:06,  1.83s/it]\n 50%|████▉     | 99/200 [03:20<02:17,  1.36s/it]\n 50%|█████     | 100/200 [03:23<03:16,  1.97s/it]\n 50%|█████     | 101/200 [03:27<03:56,  2.39s/it]\n 51%|█████     | 102/200 [03:30<04:26,  2.72s/it]\n 52%|█████▏    | 103/200 [03:34<04:43,  2.93s/it]\n 52%|█████▏    | 104/200 [03:37<04:50,  3.03s/it]\n 52%|█████▎    | 105/200 [03:40<05:01,  3.18s/it]\n 53%|█████▎    | 106/200 [03:40<03:32,  2.26s/it]\n 54%|█████▎    | 107/200 [03:44<04:00,  2.59s/it]\n 54%|█████▍    | 108/200 [03:47<04:22,  2.85s/it]\n 55%|█████▍    | 109/200 [03:51<04:35,  3.03s/it]\n 55%|█████▌    | 110/200 [03:51<03:18,  2.20s/it]\n 56%|█████▌    | 111/200 [03:51<02:24,  1.62s/it]\n 56%|█████▌    | 112/200 [03:51<01:46,  1.21s/it]\n 56%|█████▋    | 113/200 [03:55<02:41,  1.85s/it]\n 57%|█████▋    | 114/200 [03:58<03:24,  2.38s/it]\n 57%|█████▊    | 115/200 [03:59<02:24,  1.70s/it]\n 58%|█████▊    | 116/200 [04:02<03:07,  2.23s/it]\n 58%|█████▊    | 117/200 [04:05<03:33,  2.57s/it]\n 59%|█████▉    | 118/200 [04:06<02:30,  1.84s/it]\n 60%|█████▉    | 119/200 [04:09<03:09,  2.34s/it]\n 60%|██████    | 120/200 [04:13<03:38,  2.74s/it]\n 60%|██████    | 121/200 [04:16<03:49,  2.91s/it]\n 61%|██████    | 122/200 [04:16<02:41,  2.07s/it]\n 62%|██████▏   | 123/200 [04:20<03:11,  2.49s/it]\n 62%|██████▏   | 124/200 [04:23<03:30,  2.77s/it]\n 62%|██████▎   | 125/200 [04:23<02:28,  1.98s/it]\n 63%|██████▎   | 126/200 [04:27<03:00,  2.45s/it]\n 64%|██████▎   | 127/200 [04:30<03:19,  2.74s/it]\n 64%|██████▍   | 128/200 [04:30<02:20,  1.95s/it]\n 64%|██████▍   | 129/200 [04:30<01:42,  1.44s/it]\n 65%|██████▌   | 130/200 [04:34<02:22,  2.04s/it]\n 66%|██████▌   | 131/200 [04:34<01:43,  1.50s/it]\n 66%|██████▌   | 132/200 [04:38<02:20,  2.07s/it]\n 66%|██████▋   | 133/200 [04:38<01:41,  1.52s/it]\n 67%|██████▋   | 134/200 [04:41<02:17,  2.08s/it]\n 68%|██████▊   | 135/200 [04:45<02:40,  2.47s/it]\n 68%|██████▊   | 136/200 [04:48<02:55,  2.74s/it]\n 68%|██████▊   | 137/200 [04:51<03:07,  2.98s/it]\n 69%|██████▉   | 138/200 [04:55<03:10,  3.07s/it]\n 70%|██████▉   | 139/200 [04:58<03:13,  3.17s/it]\n 70%|███████   | 140/200 [05:01<03:13,  3.22s/it]\n 70%|███████   | 141/200 [05:02<02:15,  2.29s/it]\n 71%|███████   | 142/200 [05:02<01:37,  1.68s/it]\n 72%|███████▏  | 143/200 [05:05<02:05,  2.19s/it]\n 72%|███████▏  | 144/200 [05:06<01:30,  1.62s/it]\n 72%|███████▎  | 145/200 [05:09<02:00,  2.18s/it]\n 73%|███████▎  | 146/200 [05:13<02:20,  2.60s/it]\n 74%|███████▎  | 147/200 [05:13<01:38,  1.86s/it]\n 74%|███████▍  | 148/200 [05:13<01:11,  1.38s/it]\n 74%|███████▍  | 149/200 [05:16<01:40,  1.96s/it]\n 75%|███████▌  | 150/200 [05:20<01:59,  2.39s/it]\n 76%|███████▌  | 151/200 [05:23<02:12,  2.70s/it]\n 76%|███████▌  | 152/200 [05:23<01:32,  1.93s/it]\n 76%|███████▋  | 153/200 [05:27<01:53,  2.41s/it]\n 77%|███████▋  | 154/200 [05:27<01:19,  1.73s/it]\n 78%|███████▊  | 155/200 [05:27<00:57,  1.29s/it]\n 78%|███████▊  | 156/200 [05:27<00:43,  1.02it/s]\n 78%|███████▊  | 157/200 [05:31<01:14,  1.73s/it]\n 79%|███████▉  | 158/200 [05:34<01:33,  2.21s/it]\n 80%|███████▉  | 159/200 [05:35<01:06,  1.63s/it]\n 80%|████████  | 160/200 [05:35<00:48,  1.22s/it]\n 80%|████████  | 161/200 [05:38<01:12,  1.87s/it]\n 81%|████████  | 162/200 [05:42<01:29,  2.36s/it]\n 82%|████████▏ | 163/200 [05:45<01:37,  2.65s/it]\n 82%|████████▏ | 164/200 [05:45<01:08,  1.89s/it]\n 82%|████████▎ | 165/200 [05:49<01:24,  2.40s/it]\n 83%|████████▎ | 166/200 [05:52<01:31,  2.69s/it]\n 84%|████████▎ | 167/200 [05:52<01:03,  1.92s/it]\n 84%|████████▍ | 168/200 [05:52<00:45,  1.42s/it]\n 84%|████████▍ | 169/200 [05:56<01:01,  2.00s/it]\n 85%|████████▌ | 170/200 [05:56<00:44,  1.47s/it]\n 86%|████████▌ | 171/200 [06:00<01:00,  2.08s/it]\n 86%|████████▌ | 172/200 [06:03<01:09,  2.47s/it]\n 86%|████████▋ | 173/200 [06:07<01:15,  2.81s/it]\n 87%|████████▋ | 174/200 [06:10<01:18,  3.01s/it]\n 88%|████████▊ | 175/200 [06:13<01:16,  3.06s/it]\n 88%|████████▊ | 176/200 [06:13<00:53,  2.21s/it]\n 88%|████████▊ | 177/200 [06:14<00:37,  1.62s/it]\n 89%|████████▉ | 178/200 [06:17<00:47,  2.16s/it]\n 90%|████████▉ | 179/200 [06:17<00:33,  1.58s/it]\n 90%|█████████ | 180/200 [06:18<00:23,  1.18s/it]\n 90%|█████████ | 181/200 [06:18<00:17,  1.10it/s]\n 91%|█████████ | 182/200 [06:18<00:12,  1.40it/s]\n 92%|█████████▏| 183/200 [06:22<00:26,  1.53s/it]\n 92%|█████████▏| 184/200 [06:22<00:18,  1.14s/it]\n 92%|█████████▎| 185/200 [06:25<00:27,  1.81s/it]\n 93%|█████████▎| 186/200 [06:25<00:18,  1.34s/it]\n 94%|█████████▎| 187/200 [06:26<00:13,  1.02s/it]\n 94%|█████████▍| 188/200 [06:26<00:09,  1.26it/s]\n 94%|█████████▍| 189/200 [06:29<00:17,  1.60s/it]\n 95%|█████████▌| 190/200 [06:33<00:21,  2.17s/it]\n 96%|█████████▌| 191/200 [06:36<00:22,  2.52s/it]\n 96%|█████████▌| 192/200 [06:40<00:22,  2.79s/it]\n 96%|█████████▋| 193/200 [06:40<00:13,  1.99s/it]\n 97%|█████████▋| 194/200 [06:43<00:14,  2.44s/it]\n 98%|█████████▊| 195/200 [06:47<00:13,  2.71s/it]\n 98%|█████████▊| 196/200 [06:50<00:11,  2.92s/it]\n 98%|█████████▊| 197/200 [06:53<00:09,  3.06s/it]\n 99%|█████████▉| 198/200 [06:57<00:06,  3.15s/it]\n100%|█████████▉| 199/200 [07:00<00:03,  3.22s/it]\n100%|██████████| 200/200 [07:00<00:00,  2.29s/it]\n100%|██████████| 200/200 [07:00<00:00,  2.10s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751608530/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_1751608530/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_1751608530/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_1751608530/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : 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 : 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 : 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 : 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 (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 420.7585747241974\nerrors 82\nmean length: 1.77\n\nthroughput (request / second): 0.4753319647284617\nthroughput (character / second): 0.8413375775693772\naverage request duration (s) 2.1036777722835542\n50%ile request duration (s) 3.3460304737091064\n75%ile request duration (s) 3.4067702293395996\n90%ile request duration (s) 3.5050193786621096\n95%ile request duration (s) 3.5344961881637573\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-llama-8b-nis-ft-73782-v1-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ft-73782-v1-profiler
Service chaiml-llama-8b-nis-ft-73782-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.79s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-nis-ft-73782-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.49s
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-llama-8b-nis-ft-73782-v1-profiler
Waiting for inference service chaiml-llama-8b-nis-ft-73782-v1-profiler to be ready
Inference service chaiml-llama-8b-nis-ft-73782-v1-profiler ready after 222.18951416015625s
Pipeline stage MKMLProfilerDeployer completed in 222.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6:/code/chaiverse_profiler_1751609248 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751609248 && 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_1751609248/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6:/code/chaiverse_profiler_1751609688 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751609688 && 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_1751609688/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6:/code/chaiverse_profiler_1751610130 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-5deee00cb1d51b90b02e2ac73a4f1545-deplo5dzw6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751610130 && 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_1751610130/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<13:01,  3.93s/it]\n  1%|          | 2/200 [00:07<12:37,  3.83s/it]\n  2%|▏         | 3/200 [00:07<07:01,  2.14s/it]\n  2%|▏         | 4/200 [00:08<04:34,  1.40s/it]\n  2%|▎         | 5/200 [00:11<07:15,  2.23s/it]\n  3%|▎         | 6/200 [00:15<09:05,  2.81s/it]\n  4%|▎         | 7/200 [00:19<10:09,  3.16s/it]\n  4%|▍         | 8/200 [00:23<10:31,  3.29s/it]\n  4%|▍         | 9/200 [00:26<10:53,  3.42s/it]\n  5%|▌         | 10/200 [00:30<11:16,  3.56s/it]\n  6%|▌         | 11/200 [00:34<11:21,  3.61s/it]\n  6%|▌         | 12/200 [00:34<07:59,  2.55s/it]\n  6%|▋         | 13/200 [00:38<09:15,  2.97s/it]\n  7%|▋         | 14/200 [00:38<06:33,  2.12s/it]\n  8%|▊         | 15/200 [00:42<08:13,  2.67s/it]\n  8%|▊         | 16/200 [00:46<09:00,  2.93s/it]\n  8%|▊         | 17/200 [00:46<06:22,  2.09s/it]\n  9%|▉         | 18/200 [00:46<04:41,  1.55s/it]\n 10%|▉         | 19/200 [00:50<06:33,  2.17s/it]\n 10%|█         | 20/200 [00:50<04:48,  1.60s/it]\n 10%|█         | 21/200 [00:54<06:37,  2.22s/it]\n 11%|█         | 22/200 [00:57<08:00,  2.70s/it]\n 12%|█▏        | 23/200 [00:58<05:42,  1.93s/it]\n 12%|█▏        | 24/200 [01:01<07:23,  2.52s/it]\n 12%|█▎        | 25/200 [01:05<08:09,  2.80s/it]\n 13%|█▎        | 26/200 [01:09<08:57,  3.09s/it]\n 14%|█▎        | 27/200 [01:09<06:20,  2.20s/it]\n 14%|█▍        | 28/200 [01:13<07:36,  2.65s/it]\n 14%|█▍        | 29/200 [01:13<05:30,  1.94s/it]\n 15%|█▌        | 30/200 [01:13<04:04,  1.44s/it]\n 16%|█▌        | 31/200 [01:17<05:52,  2.09s/it]\n 16%|█▌        | 32/200 [01:20<07:04,  2.53s/it]\n 16%|█▋        | 33/200 [01:21<05:08,  1.85s/it]\n 17%|█▋        | 34/200 [01:21<03:49,  1.38s/it]\n 18%|█▊        | 35/200 [01:24<05:35,  2.04s/it]\n 18%|█▊        | 36/200 [01:28<06:48,  2.49s/it]\n 18%|█▊        | 37/200 [01:28<04:55,  1.82s/it]\n 19%|█▉        | 38/200 [01:32<06:20,  2.35s/it]\n 20%|█▉        | 39/200 [01:35<07:21,  2.74s/it]\n 20%|██        | 40/200 [01:36<05:22,  2.02s/it]\n 20%|██        | 41/200 [01:39<06:38,  2.51s/it]\n 21%|██        | 42/200 [01:43<07:27,  2.83s/it]\n 22%|██▏       | 43/200 [01:43<05:23,  2.06s/it]\n 22%|██▏       | 44/200 [01:43<03:57,  1.52s/it]\n 22%|██▎       | 45/200 [01:47<05:28,  2.12s/it]\n 23%|██▎       | 46/200 [01:51<06:30,  2.54s/it]\n 24%|██▎       | 47/200 [01:51<04:45,  1.86s/it]\n 24%|██▍       | 48/200 [01:54<05:59,  2.37s/it]\n 24%|██▍       | 49/200 [01:54<04:16,  1.70s/it]\n 25%|██▌       | 50/200 [01:58<05:42,  2.28s/it]\n 26%|██▌       | 51/200 [02:02<06:34,  2.65s/it]\n 26%|██▌       | 52/200 [02:05<07:10,  2.91s/it]\n 26%|██▋       | 53/200 [02:05<05:05,  2.08s/it]\n 27%|██▋       | 54/200 [02:06<03:44,  1.54s/it]\n 28%|██▊       | 55/200 [02:06<02:48,  1.16s/it]\n 28%|██▊       | 56/200 [02:09<04:33,  1.90s/it]\n 28%|██▊       | 57/200 [02:13<05:42,  2.39s/it]\n 29%|██▉       | 58/200 [02:13<04:09,  1.76s/it]\n 30%|██▉       | 59/200 [02:17<05:22,  2.29s/it]\n 30%|███       | 60/200 [02:20<06:14,  2.67s/it]\n 30%|███       | 61/200 [02:24<06:44,  2.91s/it]\n 31%|███       | 62/200 [02:27<07:04,  3.07s/it]\n 32%|███▏      | 63/200 [02:31<07:17,  3.19s/it]\n 32%|███▏      | 64/200 [02:34<07:34,  3.34s/it]\n 32%|███▎      | 65/200 [02:35<05:20,  2.38s/it]\n 33%|███▎      | 66/200 [02:35<03:53,  1.75s/it]\n 34%|███▎      | 67/200 [02:35<02:53,  1.30s/it]\n 34%|███▍      | 68/200 [02:39<04:21,  1.98s/it]\n 34%|███▍      | 69/200 [02:39<03:11,  1.46s/it]\n 35%|███▌      | 70/200 [02:42<04:30,  2.08s/it]\n 36%|███▌      | 71/200 [02:46<05:23,  2.51s/it]\n 36%|███▌      | 72/200 [02:49<05:59,  2.81s/it]\n 36%|███▋      | 73/200 [02:50<04:20,  2.05s/it]\n 37%|███▋      | 74/200 [02:50<03:11,  1.52s/it]\n 38%|███▊      | 75/200 [02:54<04:24,  2.12s/it]\n 38%|███▊      | 76/200 [02:54<03:13,  1.56s/it]\n 38%|███▊      | 77/200 [02:57<04:26,  2.16s/it]\n 39%|███▉      | 78/200 [02:58<03:14,  1.59s/it]\n 40%|███▉      | 79/200 [02:58<02:25,  1.20s/it]\n 40%|████      | 80/200 [02:58<01:50,  1.08it/s]\n 40%|████      | 81/200 [02:59<01:27,  1.36it/s]\n 41%|████      | 82/200 [03:02<03:02,  1.55s/it]\n 42%|████▏     | 83/200 [03:05<04:09,  2.13s/it]\n 42%|████▏     | 84/200 [03:06<02:57,  1.53s/it]\n 42%|████▎     | 85/200 [03:06<02:12,  1.15s/it]\n 43%|████▎     | 86/200 [03:06<01:40,  1.13it/s]\n 44%|████▎     | 87/200 [03:06<01:19,  1.42it/s]\n 44%|████▍     | 88/200 [03:07<01:04,  1.74it/s]\n 44%|████▍     | 89/200 [03:10<02:40,  1.45s/it]\n 45%|████▌     | 90/200 [03:14<03:46,  2.06s/it]\n 46%|████▌     | 91/200 [03:17<04:32,  2.50s/it]\n 46%|████▌     | 92/200 [03:17<03:18,  1.83s/it]\n 46%|████▋     | 93/200 [03:21<04:13,  2.37s/it]\n 47%|████▋     | 94/200 [03:21<03:03,  1.73s/it]\n 48%|████▊     | 95/200 [03:25<03:57,  2.26s/it]\n 48%|████▊     | 96/200 [03:28<04:34,  2.64s/it]\n 48%|████▊     | 97/200 [03:29<03:19,  1.93s/it]\n 49%|████▉     | 98/200 [03:32<04:07,  2.43s/it]\n 50%|████▉     | 99/200 [03:36<04:37,  2.75s/it]\n 50%|█████     | 100/200 [03:39<04:57,  2.97s/it]\n 50%|█████     | 101/200 [03:39<03:34,  2.16s/it]\n 51%|█████     | 102/200 [03:43<04:13,  2.58s/it]\n 52%|█████▏    | 103/200 [03:47<04:38,  2.87s/it]\n 52%|█████▏    | 104/200 [03:50<04:54,  3.07s/it]\n 52%|█████▎    | 105/200 [03:50<03:31,  2.23s/it]\n 53%|█████▎    | 106/200 [03:51<02:34,  1.64s/it]\n 54%|█████▎    | 107/200 [03:54<03:26,  2.22s/it]\n 54%|█████▍    | 108/200 [03:58<03:59,  2.61s/it]\n 55%|█████▍    | 109/200 [03:58<02:53,  1.91s/it]\n 55%|█████▌    | 110/200 [04:02<03:35,  2.39s/it]\n 56%|█████▌    | 111/200 [04:02<02:32,  1.71s/it]\n 56%|█████▌    | 112/200 [04:05<03:24,  2.32s/it]\n 56%|█████▋    | 113/200 [04:09<03:54,  2.69s/it]\n 57%|█████▋    | 114/200 [04:09<02:45,  1.92s/it]\n 57%|█████▊    | 115/200 [04:09<02:01,  1.43s/it]\n 58%|█████▊    | 116/200 [04:10<01:31,  1.09s/it]\n 58%|█████▊    | 117/200 [04:13<02:32,  1.84s/it]\n 59%|█████▉    | 118/200 [04:17<03:14,  2.37s/it]\n 60%|█████▉    | 119/200 [04:17<02:20,  1.74s/it]\n 60%|██████    | 120/200 [04:21<03:04,  2.30s/it]\n 60%|██████    | 121/200 [04:21<02:14,  1.70s/it]\n 61%|██████    | 122/200 [04:21<01:40,  1.29s/it]\n 62%|██████▏   | 123/200 [04:25<02:32,  1.99s/it]\n 62%|██████▏   | 124/200 [04:25<01:52,  1.48s/it]\n 62%|██████▎   | 125/200 [04:29<02:35,  2.08s/it]\n 63%|██████▎   | 126/200 [04:32<03:06,  2.52s/it]\n 64%|██████▎   | 127/200 [04:36<03:27,  2.84s/it]\n 64%|██████▍   | 128/200 [04:40<03:44,  3.11s/it]\n 64%|██████▍   | 129/200 [04:43<03:56,  3.33s/it]\n 65%|██████▌   | 130/200 [04:44<02:46,  2.37s/it]\n 66%|██████▌   | 131/200 [04:44<02:01,  1.76s/it]\n 66%|██████▌   | 132/200 [04:48<02:38,  2.33s/it]\n 66%|██████▋   | 133/200 [04:48<01:54,  1.71s/it]\n 67%|██████▋   | 134/200 [04:52<02:32,  2.30s/it]\n 68%|██████▊   | 135/200 [04:55<02:55,  2.71s/it]\n 68%|██████▊   | 136/200 [04:55<02:03,  1.93s/it]\n 68%|██████▊   | 137/200 [04:59<02:35,  2.47s/it]\n 69%|██████▉   | 138/200 [05:03<02:53,  2.80s/it]\n 70%|██████▉   | 139/200 [05:06<03:01,  2.97s/it]\n 70%|███████   | 140/200 [05:06<02:09,  2.16s/it]\n 70%|███████   | 141/200 [05:10<02:32,  2.58s/it]\n 71%|███████   | 142/200 [05:10<01:50,  1.90s/it]\n 72%|███████▏  | 143/200 [05:14<02:19,  2.45s/it]\n 72%|███████▏  | 144/200 [05:17<02:36,  2.79s/it]\n 72%|███████▎  | 145/200 [05:21<02:49,  3.08s/it]\n 73%|███████▎  | 146/200 [05:25<02:57,  3.28s/it]\n 74%|███████▎  | 147/200 [05:25<02:03,  2.34s/it]\n 74%|███████▍  | 148/200 [05:29<02:20,  2.70s/it]\n 74%|███████▍  | 149/200 [05:32<02:33,  3.00s/it]\n 75%|███████▌  | 150/200 [05:36<02:40,  3.22s/it]\n 76%|███████▌  | 151/200 [05:40<02:43,  3.34s/it]\n 76%|███████▌  | 152/200 [05:43<02:44,  3.42s/it]\n 76%|███████▋  | 153/200 [05:47<02:45,  3.51s/it]\n 77%|███████▋  | 154/200 [05:47<01:55,  2.50s/it]\n 78%|███████▊  | 155/200 [05:48<01:23,  1.86s/it]\n 78%|███████▊  | 156/200 [05:51<01:43,  2.36s/it]\n 78%|███████▊  | 157/200 [05:55<01:56,  2.71s/it]\n 79%|███████▉  | 158/200 [05:58<02:07,  3.03s/it]\n 80%|███████▉  | 159/200 [06:02<02:13,  3.25s/it]\n 80%|████████  | 160/200 [06:06<02:13,  3.33s/it]\n 80%|████████  | 161/200 [06:09<02:12,  3.39s/it]\n 81%|████████  | 162/200 [06:09<01:31,  2.42s/it]\n 82%|████████▏ | 163/200 [06:10<01:05,  1.77s/it]\n 82%|████████▏ | 164/200 [06:13<01:23,  2.31s/it]\n 82%|████████▎ | 165/200 [06:13<00:59,  1.69s/it]\n 83%|████████▎ | 166/200 [06:14<00:43,  1.27s/it]\n 84%|████████▎ | 167/200 [06:17<01:03,  1.93s/it]\n 84%|████████▍ | 168/200 [06:17<00:45,  1.43s/it]\n 84%|████████▍ | 169/200 [06:21<01:03,  2.05s/it]\n 85%|████████▌ | 170/200 [06:24<01:15,  2.50s/it]\n 86%|████████▌ | 171/200 [06:25<00:53,  1.84s/it]\n 86%|████████▌ | 172/200 [06:28<01:06,  2.37s/it]\n 86%|████████▋ | 173/200 [06:32<01:16,  2.84s/it]\n 87%|████████▋ | 174/200 [06:36<01:19,  3.04s/it]\n 88%|████████▊ | 175/200 [06:36<00:54,  2.17s/it]\n 88%|████████▊ | 176/200 [06:36<00:38,  1.61s/it]\n 88%|████████▊ | 177/200 [06:37<00:27,  1.21s/it]\n 89%|████████▉ | 178/200 [06:40<00:42,  1.93s/it]\n 90%|████████▉ | 179/200 [06:40<00:30,  1.44s/it]\n 90%|█████████ | 180/200 [06:44<00:41,  2.09s/it]\n 90%|█████████ | 181/200 [06:48<00:48,  2.56s/it]\n 91%|█████████ | 182/200 [06:51<00:52,  2.91s/it]\n 92%|█████████▏| 183/200 [06:52<00:36,  2.12s/it]\n 92%|█████████▏| 184/200 [06:55<00:41,  2.56s/it]\n 92%|█████████▎| 185/200 [06:59<00:43,  2.90s/it]\n 93%|█████████▎| 186/200 [07:03<00:44,  3.15s/it]\n 94%|█████████▎| 187/200 [07:06<00:42,  3.28s/it]\n 94%|█████████▍| 188/200 [07:07<00:28,  2.37s/it]\n 94%|█████████▍| 189/200 [07:10<00:30,  2.76s/it]\n 95%|█████████▌| 190/200 [07:14<00:29,  3.00s/it]\n 96%|█████████▌| 191/200 [07:17<00:28,  3.17s/it]\n 96%|█████████▌| 192/200 [07:21<00:26,  3.30s/it]\n 96%|█████████▋| 193/200 [07:21<00:16,  2.39s/it]\n 97%|█████████▋| 194/200 [07:25<00:16,  2.71s/it]\n 98%|█████████▊| 195/200 [07:28<00:14,  3.00s/it]\n 98%|█████████▊| 196/200 [07:32<00:12,  3.18s/it]\n 98%|█████████▊| 197/200 [07:35<00:09,  3.27s/it]\n 99%|█████████▉| 198/200 [07:39<00:06,  3.34s/it]\n100%|█████████▉| 199/200 [07:39<00:02,  2.38s/it]\n100%|██████████| 200/200 [07:43<00:00,  2.79s/it]\n100%|██████████| 200/200 [07:43<00:00,  2.32s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751610130/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_1751610130/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_1751610130/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_1751610130/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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : 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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 463.3311116695404\nerrors 77\nmean length: 1.845\n\nthroughput (request / second): 0.4316567460348856\nthroughput (character / second): 0.7964066964343638\naverage request duration (s) 2.316482193470001\n50%ile request duration (s) 3.509509801864624\n75%ile request duration (s) 3.6048354506492615\n90%ile request duration (s) 3.7285269021987917\n95%ile request duration (s) 3.7818887352943413\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-llama-8b-nis-ft-73782-v1-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ft-73782-v1-profiler
Service chaiml-llama-8b-nis-ft-73782-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.14s
Shutdown handler de-registered
chaiml-llama-8b-nis-ft-_73782_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-ft-_73782_v1 status is now torndown due to DeploymentManager action