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-ftt-77989-v3-mkmlizer
Waiting for job on chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer to finish
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ║                                                                     ║
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: Downloaded to shared memory in 39.432s
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: Checking if ChaiML/llama_8b_nis_fttry2_new1m_50ksamp_512seq_2ep_merged already exists in ChaiML
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp029pcu9y, device:0
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: quantized model in 21.917s
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: Processed model ChaiML/llama_8b_nis_fttry2_new1m_50ksamp_512seq_2ep_merged in 61.350s
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia/config.json
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia/tokenizer.json
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-ftt-77989-v3/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 27.15it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 40.79it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:07, 36.94it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 37.01it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.54it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.76it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:11, 22.79it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:10, 24.60it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.05it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.52it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 33.19it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.14it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.71it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.40it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.74it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.06it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:09, 22.65it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 23.99it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:07, 27.94it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.59it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 32.02it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 31.26it/s]
Loading 0:  37%|███▋      | 107/291 [00:03<00:05, 33.17it/s]
Loading 0:  38%|███▊      | 111/291 [00:03<00:05, 30.13it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.00it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.51it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 35.26it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 29.48it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:05, 29.09it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 27.52it/s]
Loading 0:  50%|████▉     | 145/291 [00:04<00:04, 29.91it/s]
Loading 0:  51%|█████     | 149/291 [00:04<00:05, 27.93it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:03, 35.15it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.07it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.59it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.08it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.33it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.81it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.39it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 23.26it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.07it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.00it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.61it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.10it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.77it/s]
Loading 0:  75%|███████▌  | 219/291 [00:07<00:02, 34.27it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.78it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 32.51it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 32.91it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 23.77it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.01it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 31.88it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.53it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.91it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:00, 32.64it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 34.85it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 33.02it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.11it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 33.60it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 33.35it/s]
Loading 0:  98%|█████████▊| 285/291 [00:09<00:00, 34.86it/s]
Loading 0:  99%|█████████▉| 289/291 [00:09<00:00, 22.00it/s]
                                                            
Job chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer completed after 84.88s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-ftt-77989-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-nis-ftt-77989-v3
Waiting for inference service chaiml-llama-8b-nis-ftt-77989-v3 to be ready
Inference service chaiml-llama-8b-nis-ftt-77989-v3 ready after 220.94807481765747s
Pipeline stage MKMLDeployer completed in 221.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.808887004852295s
Received healthy response to inference request in 4.450963973999023s
Received healthy response to inference request in 3.3949553966522217s
Received healthy response to inference request in 4.026400566101074s
Received healthy response to inference request in 2.9987375736236572s
5 requests
0 failed requests
5th percentile: 3.07798113822937
10th percentile: 3.157224702835083
20th percentile: 3.315711832046509
30th percentile: 3.521244430541992
40th percentile: 3.7738224983215334
50th percentile: 4.026400566101074
60th percentile: 4.196225929260254
70th percentile: 4.366051292419433
80th percentile: 4.722548580169678
90th percentile: 5.265717792510986
95th percentile: 5.53730239868164
99th percentile: 5.754570083618164
mean time: 4.1359889030456545
Pipeline stage StressChecker completed in 21.96s
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 0.78s
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 0.75s
Shutdown handler de-registered
chaiml-llama-8b-nis-ftt_77989_v3 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler
Waiting for inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler to be ready
Inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler ready after 222.8749132156372s
Pipeline stage MKMLProfilerDeployer completed in 223.68s
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-4321076debc038a60bec1a392c43415b-deplo99h42:/code/chaiverse_profiler_1751655322 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo99h42 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751655322 && 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_1751655322/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo99h42:/code/chaiverse_profiler_1751655763 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo99h42 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751655763 && 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_1751655763/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo99h42:/code/chaiverse_profiler_1751656173 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo99h42 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751656173 && 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_1751656173/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<00:59,  3.33it/s]\n  1%|          | 2/200 [00:03<07:05,  2.15s/it]\n  2%|▏         | 3/200 [00:04<04:14,  1.29s/it]\n  2%|▏         | 4/200 [00:04<02:56,  1.11it/s]\n  2%|▎         | 5/200 [00:04<02:14,  1.45it/s]\n  3%|▎         | 6/200 [00:08<05:20,  1.65s/it]\n  4%|▎         | 7/200 [00:08<03:52,  1.21s/it]\n  4%|▍         | 8/200 [00:11<06:12,  1.94s/it]\n  4%|▍         | 9/200 [00:12<04:32,  1.43s/it]\n  5%|▌         | 10/200 [00:15<06:36,  2.09s/it]\n  6%|▌         | 11/200 [00:16<04:51,  1.54s/it]\n  6%|▌         | 12/200 [00:16<03:39,  1.17s/it]\n  6%|▋         | 13/200 [00:19<05:52,  1.89s/it]\n  7%|▋         | 14/200 [00:23<07:20,  2.37s/it]\n  8%|▊         | 15/200 [00:23<05:13,  1.70s/it]\n  8%|▊         | 16/200 [00:23<03:54,  1.28s/it]\n  8%|▊         | 17/200 [00:27<05:56,  1.95s/it]\n  9%|▉         | 18/200 [00:27<04:22,  1.44s/it]\n 10%|▉         | 19/200 [00:31<06:24,  2.12s/it]\n 10%|█         | 20/200 [00:34<07:35,  2.53s/it]\n 10%|█         | 21/200 [00:38<08:14,  2.76s/it]\n 11%|█         | 22/200 [00:41<09:00,  3.04s/it]\n 12%|█▏        | 23/200 [00:45<09:21,  3.17s/it]\n 12%|█▏        | 24/200 [00:45<06:36,  2.25s/it]\n 12%|█▎        | 25/200 [00:49<07:50,  2.69s/it]\n 13%|█▎        | 26/200 [00:49<05:33,  1.92s/it]\n 14%|█▎        | 27/200 [00:49<04:09,  1.44s/it]\n 14%|█▍        | 28/200 [00:53<05:56,  2.07s/it]\n 14%|█▍        | 29/200 [00:56<07:07,  2.50s/it]\n 15%|█▌        | 30/200 [01:00<08:06,  2.86s/it]\n 16%|█▌        | 31/200 [01:00<05:44,  2.04s/it]\n 16%|█▌        | 32/200 [01:00<04:14,  1.51s/it]\n 16%|█▋        | 33/200 [01:04<05:54,  2.12s/it]\n 17%|█▋        | 34/200 [01:04<04:21,  1.58s/it]\n 18%|█▊        | 35/200 [01:04<03:16,  1.19s/it]\n 18%|█▊        | 36/200 [01:05<02:32,  1.08it/s]\n 18%|█▊        | 37/200 [01:08<04:38,  1.71s/it]\n 19%|█▉        | 38/200 [01:12<06:01,  2.23s/it]\n 20%|█▉        | 39/200 [01:15<07:04,  2.63s/it]\n 20%|██        | 40/200 [01:16<05:10,  1.94s/it]\n 20%|██        | 41/200 [01:19<06:21,  2.40s/it]\n 21%|██        | 42/200 [01:23<07:22,  2.80s/it]\n 22%|██▏       | 43/200 [01:23<05:13,  2.00s/it]\n 22%|██▏       | 44/200 [01:23<03:53,  1.50s/it]\n 22%|██▎       | 45/200 [01:24<02:56,  1.14s/it]\n 23%|██▎       | 46/200 [01:27<04:47,  1.87s/it]\n 24%|██▎       | 47/200 [01:31<05:59,  2.35s/it]\n 24%|██▍       | 48/200 [01:31<04:22,  1.72s/it]\n 24%|██▍       | 49/200 [01:31<03:15,  1.30s/it]\n 25%|██▌       | 50/200 [01:31<02:29,  1.00it/s]\n 26%|██▌       | 51/200 [01:35<04:23,  1.77s/it]\n 26%|██▌       | 52/200 [01:38<05:36,  2.28s/it]\n 26%|██▋       | 53/200 [01:42<06:30,  2.66s/it]\n 27%|██▋       | 54/200 [01:45<07:01,  2.89s/it]\n 28%|██▊       | 55/200 [01:49<07:24,  3.06s/it]\n 28%|██▊       | 56/200 [01:52<07:37,  3.18s/it]\n 28%|██▊       | 57/200 [01:56<07:47,  3.27s/it]\n 29%|██▉       | 58/200 [01:59<08:00,  3.38s/it]\n 30%|██▉       | 59/200 [02:03<07:59,  3.40s/it]\n 30%|███       | 60/200 [02:03<05:38,  2.42s/it]\n 30%|███       | 61/200 [02:07<06:26,  2.78s/it]\n 31%|███       | 62/200 [02:07<04:34,  1.99s/it]\n 32%|███▏      | 63/200 [02:07<03:22,  1.48s/it]\n 32%|███▏      | 64/200 [02:07<02:34,  1.14s/it]\n 32%|███▎      | 65/200 [02:11<04:08,  1.84s/it]\n 33%|███▎      | 66/200 [02:11<03:05,  1.38s/it]\n 34%|███▎      | 67/200 [02:15<04:27,  2.01s/it]\n 34%|███▍      | 68/200 [02:18<05:29,  2.50s/it]\n 34%|███▍      | 69/200 [02:18<03:54,  1.79s/it]\n 35%|███▌      | 70/200 [02:22<04:59,  2.30s/it]\n 36%|███▌      | 71/200 [02:26<05:48,  2.70s/it]\n 36%|███▌      | 72/200 [02:26<04:06,  1.93s/it]\n 36%|███▋      | 73/200 [02:26<03:03,  1.45s/it]\n 37%|███▋      | 74/200 [02:26<02:18,  1.10s/it]\n 38%|███▊      | 75/200 [02:30<03:47,  1.82s/it]\n 38%|███▊      | 76/200 [02:30<02:49,  1.37s/it]\n 38%|███▊      | 77/200 [02:31<02:10,  1.06s/it]\n 39%|███▉      | 78/200 [02:31<01:43,  1.18it/s]\n 40%|███▉      | 79/200 [02:34<03:18,  1.64s/it]\n 40%|████      | 80/200 [02:38<04:24,  2.20s/it]\n 40%|████      | 81/200 [02:41<05:08,  2.59s/it]\n 41%|████      | 82/200 [02:45<05:37,  2.86s/it]\n 42%|████▏     | 83/200 [02:48<05:59,  3.07s/it]\n 42%|████▏     | 84/200 [02:49<04:19,  2.24s/it]\n 42%|████▎     | 85/200 [02:52<05:00,  2.62s/it]\n 43%|████▎     | 86/200 [02:52<03:33,  1.87s/it]\n 44%|████▎     | 87/200 [02:53<02:38,  1.41s/it]\n 44%|████▍     | 88/200 [02:56<03:47,  2.03s/it]\n 44%|████▍     | 89/200 [03:00<04:32,  2.46s/it]\n 45%|████▌     | 90/200 [03:03<05:04,  2.77s/it]\n 46%|████▌     | 91/200 [03:07<05:29,  3.02s/it]\n 46%|████▌     | 92/200 [03:10<05:43,  3.18s/it]\n 46%|████▋     | 93/200 [03:10<04:02,  2.26s/it]\n 47%|████▋     | 94/200 [03:11<02:58,  1.69s/it]\n 48%|████▊     | 95/200 [03:14<03:52,  2.22s/it]\n 48%|████▊     | 96/200 [03:18<04:35,  2.65s/it]\n 48%|████▊     | 97/200 [03:21<04:59,  2.91s/it]\n 49%|████▉     | 98/200 [03:21<03:31,  2.08s/it]\n 50%|████▉     | 99/200 [03:22<02:36,  1.55s/it]\n 50%|█████     | 100/200 [03:25<03:34,  2.14s/it]\n 50%|█████     | 101/200 [03:26<02:36,  1.58s/it]\n 51%|█████     | 102/200 [03:26<01:57,  1.20s/it]\n 52%|█████▏    | 103/200 [03:29<03:03,  1.89s/it]\n 52%|█████▏    | 104/200 [03:30<02:15,  1.41s/it]\n 52%|█████▎    | 105/200 [03:30<01:42,  1.08s/it]\n 53%|█████▎    | 106/200 [03:30<01:19,  1.18it/s]\n 54%|█████▎    | 107/200 [03:34<02:35,  1.67s/it]\n 54%|█████▍    | 108/200 [03:34<01:55,  1.26s/it]\n 55%|█████▍    | 109/200 [03:38<02:56,  1.94s/it]\n 55%|█████▌    | 110/200 [03:38<02:10,  1.46s/it]\n 56%|█████▌    | 111/200 [03:42<03:05,  2.08s/it]\n 56%|█████▌    | 112/200 [03:45<03:42,  2.53s/it]\n 56%|█████▋    | 113/200 [03:49<04:05,  2.82s/it]\n 57%|█████▋    | 114/200 [03:49<02:57,  2.06s/it]\n 57%|█████▊    | 115/200 [03:49<02:10,  1.53s/it]\n 58%|█████▊    | 116/200 [03:53<02:58,  2.12s/it]\n 58%|█████▊    | 117/200 [03:53<02:06,  1.53s/it]\n 59%|█████▉    | 118/200 [03:57<02:58,  2.18s/it]\n 60%|█████▉    | 119/200 [04:00<03:29,  2.58s/it]\n 60%|██████    | 120/200 [04:04<03:51,  2.90s/it]\n 60%|██████    | 121/200 [04:07<04:00,  3.04s/it]\n 61%|██████    | 122/200 [04:11<04:07,  3.17s/it]\n 62%|██████▏   | 123/200 [04:14<04:14,  3.30s/it]\n 62%|██████▏   | 124/200 [04:14<02:58,  2.35s/it]\n 62%|██████▎   | 125/200 [04:15<02:10,  1.74s/it]\n 63%|██████▎   | 126/200 [04:18<02:45,  2.24s/it]\n 64%|██████▎   | 127/200 [04:22<03:14,  2.67s/it]\n 64%|██████▍   | 128/200 [04:25<03:29,  2.91s/it]\n 64%|██████▍   | 129/200 [04:29<03:38,  3.08s/it]\n 65%|██████▌   | 130/200 [04:29<02:33,  2.19s/it]\n 66%|██████▌   | 131/200 [04:32<02:58,  2.59s/it]\n 66%|██████▌   | 132/200 [04:33<02:08,  1.89s/it]\n 66%|██████▋   | 133/200 [04:33<01:34,  1.42s/it]\n 67%|██████▋   | 134/200 [04:33<01:11,  1.08s/it]\n 68%|██████▊   | 135/200 [04:33<00:55,  1.18it/s]\n 68%|██████▊   | 136/200 [04:34<00:43,  1.46it/s]\n 68%|██████▊   | 137/200 [04:34<00:35,  1.76it/s]\n 69%|██████▉   | 138/200 [04:34<00:30,  2.03it/s]\n 70%|██████▉   | 139/200 [04:38<01:25,  1.40s/it]\n 70%|███████   | 140/200 [04:41<02:00,  2.01s/it]\n 70%|███████   | 141/200 [04:42<01:28,  1.51s/it]\n 71%|███████   | 142/200 [04:45<02:03,  2.12s/it]\n 72%|███████▏  | 143/200 [04:45<01:26,  1.52s/it]\n 72%|███████▏  | 144/200 [04:49<01:58,  2.12s/it]\n 72%|███████▎  | 145/200 [04:49<01:26,  1.57s/it]\n 73%|███████▎  | 146/200 [04:53<01:56,  2.16s/it]\n 74%|███████▎  | 147/200 [04:53<01:24,  1.60s/it]\n 74%|███████▍  | 148/200 [04:56<01:52,  2.16s/it]\n 74%|███████▍  | 149/200 [05:00<02:10,  2.56s/it]\n 75%|███████▌  | 150/200 [05:04<02:22,  2.86s/it]\n 76%|███████▌  | 151/200 [05:04<01:42,  2.08s/it]\n 76%|███████▌  | 152/200 [05:07<02:00,  2.51s/it]\n 76%|███████▋  | 153/200 [05:08<01:27,  1.85s/it]\n 77%|███████▋  | 154/200 [05:11<01:50,  2.40s/it]\n 78%|███████▊  | 155/200 [05:11<01:17,  1.72s/it]\n 78%|███████▊  | 156/200 [05:12<00:56,  1.29s/it]\n 78%|███████▊  | 157/200 [05:12<00:43,  1.00s/it]\n 79%|███████▉  | 158/200 [05:16<01:14,  1.77s/it]\n 80%|███████▉  | 159/200 [05:19<01:35,  2.34s/it]\n 80%|████████  | 160/200 [05:23<01:47,  2.68s/it]\n 80%|████████  | 161/200 [05:23<01:14,  1.92s/it]\n 81%|████████  | 162/200 [05:23<00:54,  1.44s/it]\n 82%|████████▏ | 163/200 [05:24<00:40,  1.10s/it]\n 82%|████████▏ | 164/200 [05:24<00:31,  1.16it/s]\n 82%|████████▎ | 165/200 [05:24<00:24,  1.42it/s]\n 83%|████████▎ | 166/200 [05:28<00:53,  1.58s/it]\n 84%|████████▎ | 167/200 [05:28<00:39,  1.20s/it]\n 84%|████████▍ | 168/200 [05:28<00:29,  1.07it/s]\n 84%|████████▍ | 169/200 [05:32<00:53,  1.71s/it]\n 85%|████████▌ | 170/200 [05:32<00:39,  1.30s/it]\n 86%|████████▌ | 171/200 [05:36<00:57,  1.97s/it]\n 86%|████████▌ | 172/200 [05:39<01:08,  2.43s/it]\n 86%|████████▋ | 173/200 [05:43<01:15,  2.78s/it]\n 87%|████████▋ | 174/200 [05:43<00:51,  1.99s/it]\n 88%|████████▊ | 175/200 [05:43<00:36,  1.48s/it]\n 88%|████████▊ | 176/200 [05:47<00:50,  2.09s/it]\n 88%|████████▊ | 177/200 [05:47<00:35,  1.55s/it]\n 89%|████████▉ | 178/200 [05:51<00:46,  2.10s/it]\n 90%|████████▉ | 179/200 [05:54<00:52,  2.51s/it]\n 90%|█████████ | 180/200 [05:58<00:56,  2.85s/it]\n 90%|█████████ | 181/200 [06:01<00:58,  3.06s/it]\n 91%|█████████ | 182/200 [06:01<00:39,  2.18s/it]\n 92%|█████████▏| 183/200 [06:05<00:44,  2.62s/it]\n 92%|█████████▏| 184/200 [06:05<00:29,  1.87s/it]\n 92%|█████████▎| 185/200 [06:09<00:36,  2.42s/it]\n 93%|█████████▎| 186/200 [06:12<00:38,  2.77s/it]\n 94%|█████████▎| 187/200 [06:13<00:25,  1.98s/it]\n 94%|█████████▍| 188/200 [06:16<00:29,  2.44s/it]\n 94%|█████████▍| 189/200 [06:20<00:30,  2.81s/it]\n 95%|█████████▌| 190/200 [06:20<00:20,  2.01s/it]\n 96%|█████████▌| 191/200 [06:24<00:22,  2.52s/it]\n 96%|█████████▌| 192/200 [06:24<00:14,  1.80s/it]\n 96%|█████████▋| 193/200 [06:27<00:16,  2.39s/it]\n 97%|█████████▋| 194/200 [06:28<00:10,  1.71s/it]\n 98%|█████████▊| 195/200 [06:31<00:11,  2.31s/it]\n 98%|█████████▊| 196/200 [06:31<00:06,  1.66s/it]\n 98%|█████████▊| 197/200 [06:35<00:06,  2.26s/it]\n 99%|█████████▉| 198/200 [06:39<00:05,  2.63s/it]\n100%|█████████▉| 199/200 [06:42<00:02,  2.92s/it]\n100%|██████████| 200/200 [06:46<00:00,  3.08s/it]\n100%|██████████| 200/200 [06:46<00:00,  2.03s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751656173/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_1751656173/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_1751656173/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_1751656173/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 406.15277910232544\nerrors 92\nmean length: 1.62\n\nthroughput (request / second): 0.4924255361296256\nthroughput (character / second): 0.7977293685299934\naverage request duration (s) 2.030588196516037\n50%ile request duration (s) 3.4415496587753296\n75%ile request duration (s) 3.527614116668701\n90%ile request duration (s) 3.634781289100647\n95%ile request duration (s) 3.6807607054710387\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-ftt-77989-v3-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler
Service chaiml-llama-8b-nis-ftt-77989-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.41s
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-ftt-77989-v3-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.19s
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-ftt-77989-v3-profiler
Waiting for inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler to be ready
Inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler ready after 222.63575792312622s
Pipeline stage MKMLProfilerDeployer completed in 223.15s
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-4321076debc038a60bec1a392c43415b-deplo7glzv:/code/chaiverse_profiler_1751656907 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo7glzv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751656907 && 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_1751656907/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo7glzv:/code/chaiverse_profiler_1751657355 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo7glzv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751657355 && 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_1751657355/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo7glzv:/code/chaiverse_profiler_1751657797 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplo7glzv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751657797 && 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_1751657797/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n  0%|          | 0/200 [00:00<?, ?it/s]\n  0%|          | 1/200 [00:03<11:18,  3.41s/it]\n  1%|          | 2/200 [00:07<11:37,  3.52s/it]\n  2%|▏         | 3/200 [00:07<06:28,  1.97s/it]\n  2%|▏         | 4/200 [00:10<08:27,  2.59s/it]\n  2%|▎         | 5/200 [00:10<05:40,  1.75s/it]\n  3%|▎         | 6/200 [00:14<07:49,  2.42s/it]\n  4%|▎         | 7/200 [00:18<08:52,  2.76s/it]\n  4%|▍         | 8/200 [00:18<06:09,  1.92s/it]\n  4%|▍         | 9/200 [00:18<04:28,  1.41s/it]\n  5%|▌         | 10/200 [00:22<06:32,  2.06s/it]\n  6%|▌         | 11/200 [00:22<04:45,  1.51s/it]\n  6%|▌         | 12/200 [00:25<06:38,  2.12s/it]\n  6%|▋         | 13/200 [00:29<07:55,  2.54s/it]\n  7%|▋         | 14/200 [00:32<08:46,  2.83s/it]\n  8%|▊         | 15/200 [00:36<09:21,  3.04s/it]\n  8%|▊         | 16/200 [00:39<09:52,  3.22s/it]\n  8%|▊         | 17/200 [00:40<06:58,  2.29s/it]\n  9%|▉         | 18/200 [00:40<05:05,  1.68s/it]\n 10%|▉         | 19/200 [00:43<06:42,  2.22s/it]\n 10%|█         | 20/200 [00:44<04:54,  1.63s/it]\n 10%|█         | 21/200 [00:47<06:31,  2.18s/it]\n 11%|█         | 22/200 [00:51<07:44,  2.61s/it]\n 12%|█▏        | 23/200 [00:51<05:37,  1.90s/it]\n 12%|█▏        | 24/200 [00:54<06:59,  2.38s/it]\n 12%|█▎        | 25/200 [00:55<05:04,  1.74s/it]\n 13%|█▎        | 26/200 [00:58<06:35,  2.27s/it]\n 14%|█▎        | 27/200 [00:58<04:48,  1.67s/it]\n 14%|█▍        | 28/200 [00:59<03:35,  1.25s/it]\n 14%|█▍        | 29/200 [01:02<05:29,  1.93s/it]\n 15%|█▌        | 30/200 [01:03<04:03,  1.43s/it]\n 16%|█▌        | 31/200 [01:06<05:46,  2.05s/it]\n 16%|█▌        | 32/200 [01:09<06:55,  2.47s/it]\n 16%|█▋        | 33/200 [01:13<07:44,  2.78s/it]\n 17%|█▋        | 34/200 [01:13<05:36,  2.03s/it]\n 18%|█▊        | 35/200 [01:17<06:45,  2.46s/it]\n 18%|█▊        | 36/200 [01:20<07:37,  2.79s/it]\n 18%|█▊        | 37/200 [01:24<08:10,  3.01s/it]\n 19%|█▉        | 38/200 [01:24<05:47,  2.14s/it]\n 20%|█▉        | 39/200 [01:28<06:57,  2.59s/it]\n 20%|██        | 40/200 [01:28<04:56,  1.85s/it]\n 20%|██        | 41/200 [01:31<06:20,  2.39s/it]\n 21%|██        | 42/200 [01:31<04:30,  1.71s/it]\n 22%|██▏       | 43/200 [01:35<06:02,  2.31s/it]\n 22%|██▏       | 44/200 [01:35<04:17,  1.65s/it]\n 22%|██▎       | 45/200 [01:36<03:12,  1.24s/it]\n 23%|██▎       | 46/200 [01:39<04:56,  1.92s/it]\n 24%|██▎       | 47/200 [01:43<06:13,  2.44s/it]\n 24%|██▍       | 48/200 [01:43<04:25,  1.75s/it]\n 24%|██▍       | 49/200 [01:43<03:17,  1.31s/it]\n 25%|██▌       | 50/200 [01:47<04:54,  1.96s/it]\n 26%|██▌       | 51/200 [01:50<06:05,  2.46s/it]\n 26%|██▌       | 52/200 [01:54<06:50,  2.77s/it]\n 26%|██▋       | 53/200 [01:54<04:51,  1.98s/it]\n 27%|██▋       | 54/200 [01:58<06:01,  2.48s/it]\n 28%|██▊       | 55/200 [02:01<06:44,  2.79s/it]\n 28%|██▊       | 56/200 [02:05<07:11,  2.99s/it]\n 28%|██▊       | 57/200 [02:05<05:05,  2.13s/it]\n 29%|██▉       | 58/200 [02:08<05:58,  2.53s/it]\n 30%|██▉       | 59/200 [02:12<06:42,  2.85s/it]\n 30%|███       | 60/200 [02:15<07:05,  3.04s/it]\n 30%|███       | 61/200 [02:19<07:21,  3.17s/it]\n 31%|███       | 62/200 [02:22<07:30,  3.26s/it]\n 32%|███▏      | 63/200 [02:26<07:36,  3.33s/it]\n 32%|███▏      | 64/200 [02:29<07:39,  3.38s/it]\n 32%|███▎      | 65/200 [02:29<05:24,  2.41s/it]\n 33%|███▎      | 66/200 [02:30<03:56,  1.77s/it]\n 34%|███▎      | 67/200 [02:30<02:55,  1.32s/it]\n 34%|███▍      | 68/200 [02:33<04:22,  1.99s/it]\n 34%|███▍      | 69/200 [02:34<03:12,  1.47s/it]\n 35%|███▌      | 70/200 [02:37<04:31,  2.09s/it]\n 36%|███▌      | 71/200 [02:41<05:22,  2.50s/it]\n 36%|███▌      | 72/200 [02:44<05:58,  2.80s/it]\n 36%|███▋      | 73/200 [02:44<04:18,  2.04s/it]\n 37%|███▋      | 74/200 [02:45<03:09,  1.51s/it]\n 38%|███▊      | 75/200 [02:45<02:21,  1.14s/it]\n 38%|███▊      | 76/200 [02:45<01:49,  1.14it/s]\n 38%|███▊      | 77/200 [02:45<01:26,  1.42it/s]\n 39%|███▉      | 78/200 [02:46<01:10,  1.74it/s]\n 40%|███▉      | 79/200 [02:49<02:56,  1.46s/it]\n 40%|████      | 80/200 [02:53<04:07,  2.06s/it]\n 40%|████      | 81/200 [02:56<04:54,  2.48s/it]\n 41%|████      | 82/200 [02:56<03:33,  1.81s/it]\n 42%|████▏     | 83/200 [03:00<04:31,  2.32s/it]\n 42%|████▏     | 84/200 [03:03<05:10,  2.67s/it]\n 42%|████▎     | 85/200 [03:07<05:37,  2.93s/it]\n 43%|████▎     | 86/200 [03:11<05:55,  3.12s/it]\n 44%|████▎     | 87/200 [03:11<04:10,  2.22s/it]\n 44%|████▍     | 88/200 [03:14<04:57,  2.65s/it]\n 44%|████▍     | 89/200 [03:14<03:30,  1.90s/it]\n 45%|████▌     | 90/200 [03:18<04:25,  2.42s/it]\n 46%|████▌     | 91/200 [03:22<04:58,  2.74s/it]\n 46%|████▌     | 92/200 [03:25<05:19,  2.96s/it]\n 46%|████▋     | 93/200 [03:29<05:34,  3.13s/it]\n 47%|████▋     | 94/200 [03:29<03:56,  2.23s/it]\n 48%|████▊     | 95/200 [03:32<04:35,  2.63s/it]\n 48%|████▊     | 96/200 [03:36<04:59,  2.88s/it]\n 48%|████▊     | 97/200 [03:39<05:14,  3.06s/it]\n 49%|████▉     | 98/200 [03:43<05:23,  3.18s/it]\n 50%|████▉     | 99/200 [03:43<03:48,  2.26s/it]\n 50%|█████     | 100/200 [03:43<02:46,  1.66s/it]\n 50%|█████     | 101/200 [03:46<03:37,  2.20s/it]\n 51%|█████     | 102/200 [03:47<02:38,  1.62s/it]\n 52%|█████▏    | 103/200 [03:50<03:30,  2.18s/it]\n 52%|█████▏    | 104/200 [03:50<02:33,  1.60s/it]\n 52%|█████▎    | 105/200 [03:51<01:54,  1.20s/it]\n 53%|█████▎    | 106/200 [03:54<02:58,  1.90s/it]\n 54%|█████▎    | 107/200 [03:55<02:11,  1.42s/it]\n 54%|█████▍    | 108/200 [03:55<01:38,  1.08s/it]\n 55%|█████▍    | 109/200 [03:55<01:16,  1.19it/s]\n 55%|█████▌    | 110/200 [03:55<01:00,  1.49it/s]\n 56%|█████▌    | 111/200 [03:59<02:15,  1.53s/it]\n 56%|█████▌    | 112/200 [04:02<03:08,  2.14s/it]\n 56%|█████▋    | 113/200 [04:06<03:40,  2.54s/it]\n 57%|█████▋    | 114/200 [04:06<02:35,  1.81s/it]\n 57%|█████▊    | 115/200 [04:10<03:16,  2.31s/it]\n 58%|█████▊    | 116/200 [04:13<03:47,  2.71s/it]\n 58%|█████▊    | 117/200 [04:17<04:04,  2.94s/it]\n 59%|█████▉    | 118/200 [04:20<04:14,  3.11s/it]\n 60%|█████▉    | 119/200 [04:24<04:21,  3.22s/it]\n 60%|██████    | 120/200 [04:27<04:26,  3.33s/it]\n 60%|██████    | 121/200 [04:27<03:06,  2.37s/it]\n 61%|██████    | 122/200 [04:28<02:15,  1.74s/it]\n 62%|██████▏   | 123/200 [04:28<01:39,  1.30s/it]\n 62%|██████▏   | 124/200 [04:31<02:26,  1.93s/it]\n 62%|██████▎   | 125/200 [04:35<03:00,  2.41s/it]\n 63%|██████▎   | 126/200 [04:35<02:10,  1.77s/it]\n 64%|██████▎   | 127/200 [04:35<01:36,  1.32s/it]\n 64%|██████▍   | 128/200 [04:39<02:22,  1.98s/it]\n 64%|██████▍   | 129/200 [04:39<01:43,  1.46s/it]\n 65%|██████▌   | 130/200 [04:39<01:17,  1.11s/it]\n 66%|██████▌   | 131/200 [04:40<00:59,  1.16it/s]\n 66%|██████▌   | 132/200 [04:43<01:52,  1.66s/it]\n 66%|██████▋   | 133/200 [04:44<01:23,  1.25s/it]\n 67%|██████▋   | 134/200 [04:44<01:00,  1.10it/s]\n 68%|██████▊   | 135/200 [04:47<01:52,  1.73s/it]\n 68%|██████▊   | 136/200 [04:51<02:21,  2.21s/it]\n 68%|██████▊   | 137/200 [04:51<01:42,  1.62s/it]\n 69%|██████▉   | 138/200 [04:55<02:17,  2.22s/it]\n 70%|██████▉   | 139/200 [04:55<01:37,  1.59s/it]\n 70%|███████   | 140/200 [04:55<01:11,  1.20s/it]\n 70%|███████   | 141/200 [04:55<00:54,  1.09it/s]\n 71%|███████   | 142/200 [04:55<00:41,  1.38it/s]\n 72%|███████▏  | 143/200 [04:59<01:28,  1.55s/it]\n 72%|███████▏  | 144/200 [05:02<01:59,  2.14s/it]\n 72%|███████▎  | 145/200 [05:03<01:26,  1.57s/it]\n 73%|███████▎  | 146/200 [05:03<01:03,  1.18s/it]\n 74%|███████▎  | 147/200 [05:06<01:39,  1.87s/it]\n 74%|███████▍  | 148/200 [05:07<01:12,  1.39s/it]\n 74%|███████▍  | 149/200 [05:07<00:53,  1.05s/it]\n 75%|███████▌  | 150/200 [05:07<00:41,  1.22it/s]\n 76%|███████▌  | 151/200 [05:11<01:18,  1.61s/it]\n 76%|███████▌  | 152/200 [05:11<00:57,  1.21s/it]\n 76%|███████▋  | 153/200 [05:11<00:41,  1.13it/s]\n 77%|███████▋  | 154/200 [05:11<00:32,  1.42it/s]\n 78%|███████▊  | 155/200 [05:12<00:25,  1.74it/s]\n 78%|███████▊  | 156/200 [05:15<01:03,  1.45s/it]\n 78%|███████▊  | 157/200 [05:19<01:28,  2.06s/it]\n 79%|███████▉  | 158/200 [05:19<01:03,  1.52s/it]\n 80%|███████▉  | 159/200 [05:23<01:28,  2.15s/it]\n 80%|████████  | 160/200 [05:26<01:42,  2.56s/it]\n 80%|████████  | 161/200 [05:29<01:50,  2.83s/it]\n 81%|████████  | 162/200 [05:33<01:54,  3.02s/it]\n 82%|████████▏ | 163/200 [05:36<01:56,  3.16s/it]\n 82%|████████▏ | 164/200 [05:40<01:58,  3.29s/it]\n 82%|████████▎ | 165/200 [05:43<01:56,  3.32s/it]\n 83%|████████▎ | 166/200 [05:47<01:54,  3.38s/it]\n 84%|████████▎ | 167/200 [05:50<01:52,  3.41s/it]\n 84%|████████▍ | 168/200 [05:51<01:17,  2.42s/it]\n 84%|████████▍ | 169/200 [05:51<00:55,  1.78s/it]\n 85%|████████▌ | 170/200 [05:54<01:08,  2.28s/it]\n 86%|████████▌ | 171/200 [05:58<01:16,  2.65s/it]\n 86%|████████▌ | 172/200 [06:01<01:20,  2.88s/it]\n 86%|████████▋ | 173/200 [06:05<01:24,  3.13s/it]\n 87%|████████▋ | 174/200 [06:05<00:57,  2.23s/it]\n 88%|████████▊ | 175/200 [06:09<01:04,  2.60s/it]\n 88%|████████▊ | 176/200 [06:12<01:10,  2.94s/it]\n 88%|████████▊ | 177/200 [06:16<01:11,  3.09s/it]\n 89%|████████▉ | 178/200 [06:16<00:48,  2.20s/it]\n 90%|████████▉ | 179/200 [06:19<00:55,  2.63s/it]\n 90%|█████████ | 180/200 [06:20<00:37,  1.88s/it]\n 90%|█████████ | 181/200 [06:20<00:26,  1.40s/it]\n 91%|█████████ | 182/200 [06:23<00:37,  2.07s/it]\n 92%|█████████▏| 183/200 [06:27<00:42,  2.49s/it]\n 92%|█████████▏| 184/200 [06:30<00:44,  2.80s/it]\n 92%|█████████▎| 185/200 [06:31<00:30,  2.00s/it]\n 93%|█████████▎| 186/200 [06:31<00:20,  1.49s/it]\n 94%|█████████▎| 187/200 [06:34<00:27,  2.09s/it]\n 94%|█████████▍| 188/200 [06:35<00:18,  1.54s/it]\n 94%|█████████▍| 189/200 [06:38<00:23,  2.16s/it]\n 95%|█████████▌| 190/200 [06:42<00:25,  2.58s/it]\n 96%|█████████▌| 191/200 [06:45<00:25,  2.83s/it]\n 96%|█████████▌| 192/200 [06:45<00:16,  2.02s/it]\n 96%|█████████▋| 193/200 [06:49<00:17,  2.47s/it]\n 97%|█████████▋| 194/200 [06:52<00:16,  2.80s/it]\n 98%|█████████▊| 195/200 [06:53<00:10,  2.00s/it]\n 98%|█████████▊| 196/200 [06:56<00:09,  2.49s/it]\n 98%|█████████▊| 197/200 [06:56<00:05,  1.78s/it]\n 99%|█████████▉| 198/200 [06:57<00:02,  1.33s/it]\n100%|█████████▉| 199/200 [06:57<00:01,  1.01s/it]\n100%|██████████| 200/200 [07:00<00:00,  1.78s/it]\n100%|██████████| 200/200 [07:00<00:00,  2.10s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751657797/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_1751657797/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_1751657797/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_1751657797/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 (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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 420.9622049331665\nerrors 86\nmean length: 1.71\n\nthroughput (request / second): 0.47510203447303\nthroughput (character / second): 0.8124244789488814\naverage request duration (s) 2.1046365129947664\n50%ile request duration (s) 3.4597660303115845\n75%ile request duration (s) 3.511919379234314\n90%ile request duration (s) 3.6087697982788085\n95%ile request duration (s) 3.640006971359253\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-ftt-77989-v3-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler
Service chaiml-llama-8b-nis-ftt-77989-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.98s
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-ftt-77989-v3-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.86s
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-ftt-77989-v3-profiler
Waiting for inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler to be ready
Inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler ready after 222.91560697555542s
Pipeline stage MKMLProfilerDeployer completed in 223.49s
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-4321076debc038a60bec1a392c43415b-deplorb2ft:/code/chaiverse_profiler_1751658524 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplorb2ft --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751658524 && 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_1751658524/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplorb2ft:/code/chaiverse_profiler_1751658942 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplorb2ft --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751658942 && 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_1751658942/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplorb2ft:/code/chaiverse_profiler_1751659344 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-4321076debc038a60bec1a392c43415b-deplorb2ft --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751659344 && 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_1751659344/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<00:55,  3.57it/s]\n  1%|          | 2/200 [00:00<00:57,  3.46it/s]\n  2%|▏         | 3/200 [00:04<05:43,  1.75s/it]\n  2%|▏         | 4/200 [00:07<07:52,  2.41s/it]\n  2%|▎         | 5/200 [00:10<09:01,  2.78s/it]\n  3%|▎         | 6/200 [00:14<09:42,  3.00s/it]\n  4%|▎         | 7/200 [00:17<10:15,  3.19s/it]\n  4%|▍         | 8/200 [00:18<07:04,  2.21s/it]\n  4%|▍         | 9/200 [00:18<05:07,  1.61s/it]\n  5%|▌         | 10/200 [00:21<06:52,  2.17s/it]\n  6%|▌         | 11/200 [00:22<04:58,  1.58s/it]\n  6%|▌         | 12/200 [00:25<06:49,  2.18s/it]\n  6%|▋         | 13/200 [00:25<04:51,  1.56s/it]\n  7%|▋         | 14/200 [00:25<03:37,  1.17s/it]\n  8%|▊         | 15/200 [00:29<05:40,  1.84s/it]\n  8%|▊         | 16/200 [00:29<04:10,  1.36s/it]\n  8%|▊         | 17/200 [00:29<03:08,  1.03s/it]\n  9%|▉         | 18/200 [00:30<02:26,  1.24it/s]\n 10%|▉         | 19/200 [00:33<04:51,  1.61s/it]\n 10%|█         | 20/200 [00:37<06:27,  2.15s/it]\n 10%|█         | 21/200 [00:37<04:44,  1.59s/it]\n 11%|█         | 22/200 [00:37<03:32,  1.19s/it]\n 12%|█▏        | 23/200 [00:41<05:29,  1.86s/it]\n 12%|█▏        | 24/200 [00:44<06:52,  2.34s/it]\n 12%|█▎        | 25/200 [00:44<05:00,  1.72s/it]\n 13%|█▎        | 26/200 [00:44<03:43,  1.28s/it]\n 14%|█▎        | 27/200 [00:45<02:49,  1.02it/s]\n 14%|█▍        | 28/200 [00:48<04:52,  1.70s/it]\n 14%|█▍        | 29/200 [00:48<03:36,  1.27s/it]\n 15%|█▌        | 30/200 [00:49<02:45,  1.03it/s]\n 16%|█▌        | 31/200 [00:49<02:09,  1.31it/s]\n 16%|█▌        | 32/200 [00:52<04:22,  1.57s/it]\n 16%|█▋        | 33/200 [00:56<05:55,  2.13s/it]\n 17%|█▋        | 34/200 [00:59<06:56,  2.51s/it]\n 18%|█▊        | 35/200 [01:00<05:02,  1.84s/it]\n 18%|█▊        | 36/200 [01:03<06:17,  2.30s/it]\n 18%|█▊        | 37/200 [01:06<07:08,  2.63s/it]\n 19%|█▉        | 38/200 [01:10<07:49,  2.90s/it]\n 20%|█▉        | 39/200 [01:10<05:32,  2.07s/it]\n 20%|██        | 40/200 [01:10<04:05,  1.53s/it]\n 20%|██        | 41/200 [01:11<03:04,  1.16s/it]\n 21%|██        | 42/200 [01:14<04:49,  1.83s/it]\n 22%|██▏       | 43/200 [01:17<06:00,  2.30s/it]\n 22%|██▏       | 44/200 [01:21<06:49,  2.62s/it]\n 22%|██▎       | 45/200 [01:24<07:30,  2.91s/it]\n 23%|██▎       | 46/200 [01:24<05:19,  2.07s/it]\n 24%|██▎       | 47/200 [01:25<03:55,  1.54s/it]\n 24%|██▍       | 48/200 [01:28<05:22,  2.12s/it]\n 24%|██▍       | 49/200 [01:28<03:55,  1.56s/it]\n 25%|██▌       | 50/200 [01:32<05:19,  2.13s/it]\n 26%|██▌       | 51/200 [01:35<06:21,  2.56s/it]\n 26%|██▌       | 52/200 [01:39<07:00,  2.84s/it]\n 26%|██▋       | 53/200 [01:42<07:26,  3.04s/it]\n 27%|██▋       | 54/200 [01:46<07:39,  3.15s/it]\n 28%|██▊       | 55/200 [01:46<05:25,  2.24s/it]\n 28%|██▊       | 56/200 [01:46<03:57,  1.65s/it]\n 28%|██▊       | 57/200 [01:46<02:56,  1.24s/it]\n 29%|██▉       | 58/200 [01:50<04:30,  1.90s/it]\n 30%|██▉       | 59/200 [01:53<05:30,  2.34s/it]\n 30%|███       | 60/200 [01:57<06:13,  2.67s/it]\n 30%|███       | 61/200 [01:57<04:31,  1.95s/it]\n 31%|███       | 62/200 [02:00<05:30,  2.39s/it]\n 32%|███▏      | 63/200 [02:04<06:11,  2.71s/it]\n 32%|███▏      | 64/200 [02:04<04:28,  1.98s/it]\n 32%|███▎      | 65/200 [02:08<05:25,  2.41s/it]\n 33%|███▎      | 66/200 [02:11<06:03,  2.72s/it]\n 34%|███▎      | 67/200 [02:14<06:28,  2.92s/it]\n 34%|███▍      | 68/200 [02:15<04:39,  2.12s/it]\n 34%|███▍      | 69/200 [02:18<05:29,  2.52s/it]\n 35%|███▌      | 70/200 [02:18<03:59,  1.84s/it]\n 36%|███▌      | 71/200 [02:22<04:57,  2.31s/it]\n 36%|███▌      | 72/200 [02:25<05:37,  2.63s/it]\n 36%|███▋      | 73/200 [02:29<06:02,  2.85s/it]\n 37%|███▋      | 74/200 [02:32<06:21,  3.03s/it]\n 38%|███▊      | 75/200 [02:35<06:31,  3.13s/it]\n 38%|███▊      | 76/200 [02:36<04:41,  2.27s/it]\n 38%|███▊      | 77/200 [02:36<03:25,  1.67s/it]\n 39%|███▉      | 78/200 [02:36<02:33,  1.25s/it]\n 40%|███▉      | 79/200 [02:40<03:52,  1.92s/it]\n 40%|████      | 80/200 [02:40<02:51,  1.43s/it]\n 40%|████      | 81/200 [02:40<02:03,  1.03s/it]\n 41%|████      | 82/200 [02:44<03:35,  1.82s/it]\n 42%|████▏     | 83/200 [02:47<04:28,  2.29s/it]\n 42%|████▏     | 84/200 [02:47<03:10,  1.64s/it]\n 42%|████▎     | 85/200 [02:47<02:21,  1.23s/it]\n 43%|████▎     | 86/200 [02:48<01:47,  1.06it/s]\n 44%|████▎     | 87/200 [02:51<03:09,  1.68s/it]\n 44%|████▍     | 88/200 [02:55<04:07,  2.21s/it]\n 44%|████▍     | 89/200 [02:58<04:51,  2.62s/it]\n 45%|████▌     | 90/200 [03:02<05:14,  2.86s/it]\n 46%|████▌     | 91/200 [03:05<05:30,  3.03s/it]\n 46%|████▌     | 92/200 [03:05<03:53,  2.16s/it]\n 46%|████▋     | 93/200 [03:09<04:32,  2.55s/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<03:43,  2.15s/it]\n 48%|████▊     | 97/200 [03:19<04:23,  2.56s/it]\n 49%|████▉     | 98/200 [03:19<03:06,  1.83s/it]\n 50%|████▉     | 99/200 [03:23<03:54,  2.32s/it]\n 50%|█████     | 100/200 [03:26<04:29,  2.69s/it]\n 50%|█████     | 101/200 [03:26<03:10,  1.92s/it]\n 51%|█████     | 102/200 [03:30<03:57,  2.42s/it]\n 52%|█████▏    | 103/200 [03:30<02:48,  1.73s/it]\n 52%|█████▏    | 104/200 [03:30<02:04,  1.30s/it]\n 52%|█████▎    | 105/200 [03:34<03:03,  1.93s/it]\n 53%|█████▎    | 106/200 [03:34<02:14,  1.43s/it]\n 54%|█████▎    | 107/200 [03:34<01:40,  1.08s/it]\n 54%|█████▍    | 108/200 [03:38<02:44,  1.79s/it]\n 55%|█████▍    | 109/200 [03:41<03:27,  2.28s/it]\n 55%|█████▌    | 110/200 [03:45<03:54,  2.60s/it]\n 56%|█████▌    | 111/200 [03:45<02:49,  1.90s/it]\n 56%|█████▌    | 112/200 [03:45<02:04,  1.42s/it]\n 56%|█████▋    | 113/200 [03:45<01:33,  1.08s/it]\n 57%|█████▋    | 114/200 [03:46<01:12,  1.19it/s]\n 57%|█████▊    | 115/200 [03:49<02:18,  1.63s/it]\n 58%|█████▊    | 116/200 [03:53<03:03,  2.18s/it]\n 58%|█████▊    | 117/200 [03:56<03:31,  2.55s/it]\n 59%|█████▉    | 118/200 [04:00<03:53,  2.85s/it]\n 60%|█████▉    | 119/200 [04:03<04:06,  3.04s/it]\n 60%|██████    | 120/200 [04:03<02:53,  2.17s/it]\n 60%|██████    | 121/200 [04:07<03:26,  2.61s/it]\n 61%|██████    | 122/200 [04:07<02:25,  1.87s/it]\n 62%|██████▏   | 123/200 [04:11<03:05,  2.41s/it]\n 62%|██████▏   | 124/200 [04:11<02:11,  1.73s/it]\n 62%|██████▎   | 125/200 [04:14<02:46,  2.22s/it]\n 63%|██████▎   | 126/200 [04:14<02:01,  1.64s/it]\n 64%|██████▎   | 127/200 [04:18<02:41,  2.21s/it]\n 64%|██████▍   | 128/200 [04:21<03:05,  2.58s/it]\n 64%|██████▍   | 129/200 [04:25<03:21,  2.84s/it]\n 65%|██████▌   | 130/200 [04:25<02:21,  2.03s/it]\n 66%|██████▌   | 131/200 [04:28<02:48,  2.44s/it]\n 66%|██████▌   | 132/200 [04:29<02:01,  1.79s/it]\n 66%|██████▋   | 133/200 [04:29<01:29,  1.33s/it]\n 67%|██████▋   | 134/200 [04:32<02:09,  1.97s/it]\n 68%|██████▊   | 135/200 [04:33<01:34,  1.45s/it]\n 68%|██████▊   | 136/200 [04:36<02:09,  2.03s/it]\n 68%|██████▊   | 137/200 [04:40<02:37,  2.50s/it]\n 69%|██████▉   | 138/200 [04:43<02:52,  2.78s/it]\n 70%|██████▉   | 139/200 [04:43<02:01,  1.99s/it]\n 70%|███████   | 140/200 [04:44<01:28,  1.48s/it]\n 70%|███████   | 141/200 [04:47<02:01,  2.05s/it]\n 71%|███████   | 142/200 [04:50<02:25,  2.50s/it]\n 72%|███████▏  | 143/200 [04:51<01:41,  1.79s/it]\n 72%|███████▏  | 144/200 [04:54<02:10,  2.33s/it]\n 72%|███████▎  | 145/200 [04:54<01:31,  1.67s/it]\n 73%|███████▎  | 146/200 [04:58<01:59,  2.22s/it]\n 74%|███████▎  | 147/200 [04:58<01:26,  1.64s/it]\n 74%|███████▍  | 148/200 [04:58<01:03,  1.23s/it]\n 74%|███████▍  | 149/200 [05:02<01:35,  1.88s/it]\n 75%|███████▌  | 150/200 [05:02<01:10,  1.40s/it]\n 76%|███████▌  | 151/200 [05:06<01:38,  2.02s/it]\n 76%|███████▌  | 152/200 [05:06<01:11,  1.49s/it]\n 76%|███████▋  | 153/200 [05:06<00:53,  1.13s/it]\n 77%|███████▋  | 154/200 [05:09<01:23,  1.81s/it]\n 78%|███████▊  | 155/200 [05:10<01:00,  1.35s/it]\n 78%|███████▊  | 156/200 [05:10<00:44,  1.02s/it]\n 78%|███████▊  | 157/200 [05:13<01:15,  1.76s/it]\n 79%|███████▉  | 158/200 [05:14<00:55,  1.31s/it]\n 80%|███████▉  | 159/200 [05:17<01:20,  1.95s/it]\n 80%|████████  | 160/200 [05:21<01:35,  2.39s/it]\n 80%|████████  | 161/200 [05:21<01:08,  1.75s/it]\n 81%|████████  | 162/200 [05:24<01:25,  2.24s/it]\n 82%|████████▏ | 163/200 [05:28<01:36,  2.61s/it]\n 82%|████████▏ | 164/200 [05:31<01:44,  2.89s/it]\n 82%|████████▎ | 165/200 [05:32<01:13,  2.11s/it]\n 83%|████████▎ | 166/200 [05:32<00:53,  1.57s/it]\n 84%|████████▎ | 167/200 [05:35<01:10,  2.13s/it]\n 84%|████████▍ | 168/200 [05:36<00:50,  1.57s/it]\n 84%|████████▍ | 169/200 [05:39<01:07,  2.16s/it]\n 85%|████████▌ | 170/200 [05:39<00:47,  1.60s/it]\n 86%|████████▌ | 171/200 [05:40<00:34,  1.21s/it]\n 86%|████████▌ | 172/200 [05:43<00:52,  1.88s/it]\n 86%|████████▋ | 173/200 [05:47<01:03,  2.37s/it]\n 87%|████████▋ | 174/200 [05:50<01:09,  2.67s/it]\n 88%|████████▊ | 175/200 [05:53<01:11,  2.85s/it]\n 88%|████████▊ | 176/200 [05:54<00:49,  2.08s/it]\n 88%|████████▊ | 177/200 [05:57<00:57,  2.51s/it]\n 89%|████████▉ | 178/200 [05:57<00:39,  1.80s/it]\n 90%|████████▉ | 179/200 [05:58<00:28,  1.34s/it]\n 90%|█████████ | 180/200 [06:01<00:39,  1.96s/it]\n 90%|█████████ | 181/200 [06:04<00:46,  2.45s/it]\n 91%|█████████ | 182/200 [06:05<00:31,  1.75s/it]\n 92%|█████████▏| 183/200 [06:05<00:22,  1.31s/it]\n 92%|█████████▏| 184/200 [06:05<00:16,  1.00s/it]\n 92%|█████████▎| 185/200 [06:09<00:25,  1.72s/it]\n 93%|█████████▎| 186/200 [06:09<00:17,  1.28s/it]\n 94%|█████████▎| 187/200 [06:09<00:12,  1.02it/s]\n 94%|█████████▍| 188/200 [06:09<00:09,  1.30it/s]\n 94%|█████████▍| 189/200 [06:13<00:17,  1.59s/it]\n 95%|█████████▌| 190/200 [06:16<00:21,  2.15s/it]\n 96%|█████████▌| 191/200 [06:17<00:14,  1.59s/it]\n 96%|█████████▌| 192/200 [06:20<00:17,  2.13s/it]\n 96%|█████████▋| 193/200 [06:20<00:11,  1.58s/it]\n 97%|█████████▋| 194/200 [06:24<00:12,  2.15s/it]\n 98%|█████████▊| 195/200 [06:27<00:12,  2.53s/it]\n 98%|█████████▊| 196/200 [06:27<00:07,  1.80s/it]\n 98%|█████████▊| 197/200 [06:28<00:04,  1.35s/it]\n 99%|█████████▉| 198/200 [06:31<00:03,  1.97s/it]\n100%|█████████▉| 199/200 [06:34<00:02,  2.42s/it]\n100%|██████████| 200/200 [06:35<00:00,  1.77s/it]\n100%|██████████| 200/200 [06:35<00:00,  1.98s/it]\nTraceback (most recent call last):\n  File "/code/chaiverse_profiler_1751659344/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_1751659344/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_1751659344/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_1751659344/profiles.py", line 277, in run_batch_profile\n    analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n  File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n    f.write(json.dumps(row) + \'\\n\')\n  File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n    return _default_encoder.encode(obj)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n    chunks = self.iterencode(o, _one_shot=True)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n    return _iterencode(o, 0)\n  File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n    raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 395.2377738952637\nerrors 92\nmean length: 1.62\n\nthroughput (request / second): 0.5060245078017243\nthroughput (character / second): 0.8197597026387934\naverage request duration (s) 1.9760686659812927\n50%ile request duration (s) 3.3775181770324707\n75%ile request duration (s) 3.4451122879981995\n90%ile request duration (s) 3.5288211584091185\n95%ile request duration (s) 3.5694814682006837\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-ftt-77989-v3-profiler is running
Tearing down inference service chaiml-llama-8b-nis-ftt-77989-v3-profiler
Service chaiml-llama-8b-nis-ftt-77989-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.43s
Shutdown handler de-registered
chaiml-llama-8b-nis-ftt_77989_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-ftt_77989_v3 status is now torndown due to DeploymentManager action