Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-llama3-200m-v2-t-76584-v3-mkmlizer
Waiting for job on chaiml-llama3-200m-v2-t-76584-v3-mkmlizer to finish
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ belonging to: ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ║ ║
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: Downloaded to shared memory in 22.467s
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: Checking if ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725 already exists in ChaiML
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmppd0bju_1, device:0
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: quantized model in 19.115s
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: Processed model ChaiML/llama3-200m-v2-try1-new8m-filterv3-4m-full-512seq-bestep-5725 in 41.582s
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia/config.json
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia/special_tokens_map.json
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia/tokenizer_config.json
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia/tokenizer.json
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama3-200m-v2-t-76584-v3/nvidia/flywheel_model.0.safetensors
chaiml-llama3-200m-v2-t-76584-v3-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 39.06it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:05, 49.71it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:04, 59.55it/s]
Loading 0: 10%|▉ | 29/291 [00:00<00:04, 56.08it/s]
Loading 0: 12%|█▏ | 35/291 [00:00<00:04, 55.17it/s]
Loading 0: 14%|█▍ | 41/291 [00:00<00:05, 43.11it/s]
Loading 0: 16%|█▋ | 48/291 [00:00<00:04, 49.33it/s]
Loading 0: 19%|█▊ | 54/291 [00:01<00:04, 48.23it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 41.54it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 46.44it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 45.09it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 45.03it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 34.01it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 33.65it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 41.04it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 42.01it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 43.45it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 49.51it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:03, 46.45it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 46.35it/s]
Loading 0: 45%|████▌ | 131/291 [00:02<00:03, 46.63it/s]
Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 54.05it/s]
Loading 0: 50%|████▉ | 145/291 [00:03<00:02, 50.16it/s]
Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 49.68it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 50.96it/s]
Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 46.60it/s]
Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 42.58it/s]
Loading 0: 59%|█████▉ | 173/291 [00:03<00:02, 42.98it/s]
Loading 0: 62%|██████▏ | 180/291 [00:03<00:02, 48.05it/s]
Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 47.01it/s]
Loading 0: 65%|██████▌ | 190/291 [00:04<00:03, 25.85it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 26.33it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 33.44it/s]
Loading 0: 71%|███████ | 206/291 [00:04<00:02, 35.20it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 37.32it/s]
Loading 0: 75%|███████▍ | 217/291 [00:05<00:01, 38.03it/s]
Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 38.80it/s]
Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 43.15it/s]
Loading 0: 80%|████████ | 233/291 [00:05<00:01, 42.56it/s]
Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 41.46it/s]
Loading 0: 84%|████████▎ | 243/291 [00:05<00:01, 43.39it/s]
Loading 0: 85%|████████▌ | 248/291 [00:05<00:01, 36.27it/s]
Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 43.64it/s]
Loading 0: 89%|████████▉ | 260/291 [00:06<00:00, 43.79it/s]
Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 43.56it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 43.16it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 43.58it/s]
Loading 0: 97%|█████████▋| 282/291 [00:06<00:00, 40.93it/s]
Loading 0: 99%|█████████▊| 287/291 [00:06<00:00, 32.61it/s]
Job chaiml-llama3-200m-v2-t-76584-v3-mkmlizer completed after 64.8s with status: succeeded
Stopping job with name chaiml-llama3-200m-v2-t-76584-v3-mkmlizer
Pipeline stage MKMLizer completed in 65.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v3
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v3 to be ready
Failed to get response for submission chaiml-mistralnemo-nis-_16053_v3: HTTPConnectionPool(host='chaiml-mistralnemo-nis-16053-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-mistralnemo-nis-_16053_v3: HTTPConnectionPool(host='chaiml-mistralnemo-nis-16053-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-llama3-200m-v2-t_76584_v2: HTTPConnectionPool(host='chaiml-llama3-200m-v2-t-76584-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama3-200m-v2-t-76584-v3 ready after 192.62960815429688s
Pipeline stage MKMLDeployer completed in 193.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.8421730995178223s
Received healthy response to inference request in 4.866883277893066s
Received healthy response to inference request in 3.772369384765625s
Received healthy response to inference request in 7.165832042694092s
Received healthy response to inference request in 3.331270933151245s
5 requests
0 failed requests
5th percentile: 3.419490623474121
10th percentile: 3.507710313796997
20th percentile: 3.684149694442749
30th percentile: 3.7863301277160644
40th percentile: 3.8142516136169435
50th percentile: 3.8421730995178223
60th percentile: 4.25205717086792
70th percentile: 4.661941242218018
80th percentile: 5.3266730308532715
90th percentile: 6.246252536773682
95th percentile: 6.706042289733887
99th percentile: 7.07387409210205
mean time: 4.59570574760437
Pipeline stage StressChecker completed in 24.38s
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 0.87s
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 1.18s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama3-200m-v2-t-76584-v3-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v3-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v3-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.55s
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-llama3-200m-v2-t-76584-v3-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v3-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v3-profiler ready after 60.7795991897583s
Pipeline stage MKMLProfilerDeployer completed in 61.35s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w:/code/chaiverse_profiler_1752092742 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752092742 && 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_1752092742/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w:/code/chaiverse_profiler_1752093202 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752093202 && 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_1752093202/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w:/code/chaiverse_profiler_1752093627 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplogn25w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752093627 && 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_1752093627/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<11:33, 3.48s/it]\n 1%| | 2/200 [00:03<05:11, 1.57s/it]\n 2%|▏ | 3/200 [00:07<08:05, 2.47s/it]\n 2%|▏ | 4/200 [00:10<09:22, 2.87s/it]\n 2%|▎ | 5/200 [00:14<10:08, 3.12s/it]\n 3%|▎ | 6/200 [00:14<06:54, 2.14s/it]\n 4%|▎ | 7/200 [00:18<08:29, 2.64s/it]\n 4%|▍ | 8/200 [00:18<05:53, 1.84s/it]\n 4%|▍ | 9/200 [00:22<07:40, 2.41s/it]\n 5%|▌ | 10/200 [00:25<08:43, 2.76s/it]\n 6%|▌ | 11/200 [00:28<09:21, 2.97s/it]\n 6%|▌ | 12/200 [00:29<06:42, 2.14s/it]\n 6%|▋ | 13/200 [00:32<07:59, 2.57s/it]\n 7%|▋ | 14/200 [00:33<05:47, 1.87s/it]\n 8%|▊ | 15/200 [00:33<04:16, 1.38s/it]\n 8%|▊ | 16/200 [00:36<06:14, 2.04s/it]\n 8%|▊ | 17/200 [00:37<04:33, 1.50s/it]\n 9%|▉ | 18/200 [00:40<06:23, 2.11s/it]\n 10%|▉ | 19/200 [00:44<07:44, 2.57s/it]\n 10%|█ | 20/200 [00:47<08:35, 2.86s/it]\n 10%|█ | 21/200 [00:51<09:16, 3.11s/it]\n 11%|█ | 22/200 [00:51<06:33, 2.21s/it]\n 12%|█▏ | 23/200 [00:55<07:48, 2.65s/it]\n 12%|█▏ | 24/200 [00:55<05:34, 1.90s/it]\n 12%|█▎ | 25/200 [00:59<07:04, 2.43s/it]\n 13%|█▎ | 26/200 [01:02<07:59, 2.75s/it]\n 14%|█▎ | 27/200 [01:02<05:40, 1.97s/it]\n 14%|█▍ | 28/200 [01:06<07:00, 2.45s/it]\n 14%|█▍ | 29/200 [01:09<08:00, 2.81s/it]\n 15%|█▌ | 30/200 [01:10<05:41, 2.01s/it]\n 16%|█▌ | 31/200 [01:13<07:03, 2.51s/it]\n 16%|█▌ | 32/200 [01:13<05:00, 1.79s/it]\n 16%|█▋ | 33/200 [01:17<06:27, 2.32s/it]\n 17%|█▋ | 34/200 [01:17<04:41, 1.70s/it]\n 18%|█▊ | 35/200 [01:17<03:29, 1.27s/it]\n 18%|█▊ | 36/200 [01:21<05:19, 1.95s/it]\n 18%|█▊ | 37/200 [01:21<03:54, 1.44s/it]\n 19%|█▉ | 38/200 [01:25<05:37, 2.09s/it]\n 20%|█▉ | 39/200 [01:28<06:47, 2.53s/it]\n 20%|██ | 40/200 [01:32<07:34, 2.84s/it]\n 20%|██ | 41/200 [01:32<05:22, 2.03s/it]\n 21%|██ | 42/200 [01:36<06:43, 2.55s/it]\n 22%|██▏ | 43/200 [01:39<07:30, 2.87s/it]\n 22%|██▏ | 44/200 [01:40<05:19, 2.05s/it]\n 22%|██▎ | 45/200 [01:43<06:29, 2.51s/it]\n 23%|██▎ | 46/200 [01:43<04:43, 1.84s/it]\n 24%|██▎ | 47/200 [01:47<05:58, 2.34s/it]\n 24%|██▍ | 48/200 [01:51<07:01, 2.77s/it]\n 24%|██▍ | 49/200 [01:54<07:31, 2.99s/it]\n 25%|██▌ | 50/200 [01:58<07:52, 3.15s/it]\n 26%|██▌ | 51/200 [01:58<05:35, 2.25s/it]\n 26%|██▌ | 52/200 [02:02<06:35, 2.67s/it]\n 26%|██▋ | 53/200 [02:05<07:21, 3.00s/it]\n 27%|██▋ | 54/200 [02:06<05:13, 2.15s/it]\n 28%|██▊ | 55/200 [02:06<03:50, 1.59s/it]\n 28%|██▊ | 56/200 [02:09<05:16, 2.20s/it]\n 28%|██▊ | 57/200 [02:10<03:50, 1.61s/it]\n 29%|██▉ | 58/200 [02:13<05:13, 2.21s/it]\n 30%|██▉ | 59/200 [02:17<06:12, 2.64s/it]\n 30%|███ | 60/200 [02:20<06:45, 2.90s/it]\n 30%|███ | 61/200 [02:21<04:46, 2.06s/it]\n 31%|███ | 62/200 [02:21<03:30, 1.52s/it]\n 32%|███▏ | 63/200 [02:21<02:36, 1.14s/it]\n 32%|███▏ | 64/200 [02:25<04:11, 1.85s/it]\n 32%|███▎ | 65/200 [02:25<03:04, 1.37s/it]\n 33%|███▎ | 66/200 [02:28<04:29, 2.01s/it]\n 34%|███▎ | 67/200 [02:32<05:27, 2.47s/it]\n 34%|███▍ | 68/200 [02:35<06:09, 2.80s/it]\n 34%|███▍ | 69/200 [02:39<06:39, 3.05s/it]\n 35%|███▌ | 70/200 [02:43<06:59, 3.23s/it]\n 36%|███▌ | 71/200 [02:46<07:10, 3.34s/it]\n 36%|███▌ | 72/200 [02:50<07:15, 3.40s/it]\n 36%|███▋ | 73/200 [02:53<07:16, 3.44s/it]\n 37%|███▋ | 74/200 [02:54<05:11, 2.48s/it]\n 38%|███▊ | 75/200 [02:57<05:52, 2.82s/it]\n 38%|███▊ | 76/200 [02:57<04:15, 2.06s/it]\n 38%|███▊ | 77/200 [02:58<03:08, 1.53s/it]\n 39%|███▉ | 78/200 [02:58<02:21, 1.16s/it]\n 40%|███▉ | 79/200 [03:02<03:53, 1.93s/it]\n 40%|████ | 80/200 [03:05<04:49, 2.41s/it]\n 40%|████ | 81/200 [03:06<03:29, 1.76s/it]\n 41%|████ | 82/200 [03:06<02:35, 1.32s/it]\n 42%|████▏ | 83/200 [03:06<01:57, 1.00s/it]\n 42%|████▏ | 84/200 [03:10<03:27, 1.78s/it]\n 42%|████▎ | 85/200 [03:10<02:32, 1.33s/it]\n 43%|████▎ | 86/200 [03:14<03:51, 2.03s/it]\n 44%|████▎ | 87/200 [03:17<04:46, 2.54s/it]\n 44%|████▍ | 88/200 [03:18<03:29, 1.87s/it]\n 44%|████▍ | 89/200 [03:21<04:27, 2.41s/it]\n 45%|████▌ | 90/200 [03:25<05:03, 2.76s/it]\n 46%|████▌ | 91/200 [03:25<03:38, 2.00s/it]\n 46%|████▌ | 92/200 [03:29<04:27, 2.47s/it]\n 46%|████▋ | 93/200 [03:29<03:13, 1.81s/it]\n 47%|████▋ | 94/200 [03:33<04:06, 2.33s/it]\n 48%|████▊ | 95/200 [03:33<02:59, 1.71s/it]\n 48%|████▊ | 96/200 [03:36<03:55, 2.26s/it]\n 48%|████▊ | 97/200 [03:40<04:35, 2.68s/it]\n 49%|████▉ | 98/200 [03:44<05:00, 2.95s/it]\n 50%|████▉ | 99/200 [03:44<03:37, 2.15s/it]\n 50%|█████ | 100/200 [03:44<02:34, 1.55s/it]\n 50%|█████ | 101/200 [03:44<01:55, 1.16s/it]\n 51%|█████ | 102/200 [03:48<03:03, 1.87s/it]\n 52%|█████▏ | 103/200 [03:51<03:52, 2.40s/it]\n 52%|█████▏ | 104/200 [03:55<04:27, 2.79s/it]\n 52%|█████▎ | 105/200 [03:59<04:50, 3.06s/it]\n 53%|█████▎ | 106/200 [04:03<05:05, 3.25s/it]\n 54%|█████▎ | 107/200 [04:06<05:10, 3.34s/it]\n 54%|█████▍ | 108/200 [04:06<03:38, 2.38s/it]\n 55%|█████▍ | 109/200 [04:06<02:38, 1.74s/it]\n 55%|█████▌ | 110/200 [04:10<03:26, 2.30s/it]\n 56%|█████▌ | 111/200 [04:10<02:29, 1.68s/it]\n 56%|█████▌ | 112/200 [04:14<03:22, 2.30s/it]\n 56%|█████▋ | 113/200 [04:18<03:52, 2.68s/it]\n 57%|█████▋ | 114/200 [04:21<04:18, 3.00s/it]\n 57%|█████▊ | 115/200 [04:25<04:28, 3.15s/it]\n 58%|█████▊ | 116/200 [04:25<03:09, 2.25s/it]\n 58%|█████▊ | 117/200 [04:25<02:18, 1.67s/it]\n 59%|█████▉ | 118/200 [04:29<03:09, 2.31s/it]\n 60%|█████▉ | 119/200 [04:33<03:37, 2.69s/it]\n 60%|██████ | 120/200 [04:36<03:59, 2.99s/it]\n 60%|██████ | 121/200 [04:40<04:09, 3.16s/it]\n 61%|██████ | 122/200 [04:40<02:55, 2.25s/it]\n 62%|██████▏ | 123/200 [04:44<03:31, 2.75s/it]\n 62%|██████▏ | 124/200 [04:47<03:45, 2.97s/it]\n 62%|██████▎ | 125/200 [04:51<03:59, 3.19s/it]\n 63%|██████▎ | 126/200 [04:51<02:48, 2.28s/it]\n 64%|██████▎ | 127/200 [04:55<03:18, 2.72s/it]\n 64%|██████▍ | 128/200 [04:59<03:39, 3.04s/it]\n 64%|██████▍ | 129/200 [05:02<03:47, 3.21s/it]\n 65%|██████▌ | 130/200 [05:06<03:55, 3.36s/it]\n 66%|██████▌ | 131/200 [05:10<03:55, 3.42s/it]\n 66%|██████▌ | 132/200 [05:10<02:45, 2.43s/it]\n 66%|██████▋ | 133/200 [05:14<03:07, 2.80s/it]\n 67%|██████▋ | 134/200 [05:17<03:20, 3.04s/it]\n 68%|██████▊ | 135/200 [05:21<03:30, 3.24s/it]\n 68%|██████▊ | 136/200 [05:25<03:37, 3.40s/it]\n 68%|██████▊ | 137/200 [05:29<03:43, 3.55s/it]\n 69%|██████▉ | 138/200 [05:32<03:41, 3.57s/it]\n 70%|██████▉ | 139/200 [05:36<03:39, 3.61s/it]\n 70%|███████ | 140/200 [05:39<03:37, 3.62s/it]\n 70%|███████ | 141/200 [05:43<03:33, 3.62s/it]\n 71%|███████ | 142/200 [05:43<02:29, 2.57s/it]\n 72%|███████▏ | 143/200 [05:47<02:45, 2.90s/it]\n 72%|███████▏ | 144/200 [05:47<01:58, 2.11s/it]\n 72%|███████▎ | 145/200 [05:48<01:27, 1.58s/it]\n 73%|███████▎ | 146/200 [05:48<01:05, 1.22s/it]\n 74%|███████▎ | 147/200 [05:52<01:43, 1.96s/it]\n 74%|███████▍ | 148/200 [05:52<01:16, 1.47s/it]\n 74%|███████▍ | 149/200 [05:56<01:48, 2.13s/it]\n 75%|███████▌ | 150/200 [05:56<01:19, 1.58s/it]\n 76%|███████▌ | 151/200 [06:00<01:49, 2.23s/it]\n 76%|███████▌ | 152/200 [06:03<02:06, 2.64s/it]\n 76%|███████▋ | 153/200 [06:07<02:21, 3.00s/it]\n 77%|███████▋ | 154/200 [06:11<02:29, 3.24s/it]\n 78%|███████▊ | 155/200 [06:11<01:46, 2.37s/it]\n 78%|███████▊ | 156/200 [06:12<01:17, 1.75s/it]\n 78%|███████▊ | 157/200 [06:12<00:57, 1.34s/it]\n 79%|███████▉ | 158/200 [06:12<00:43, 1.04s/it]\n 80%|███████▉ | 159/200 [06:13<00:34, 1.20it/s]\n 80%|████████ | 160/200 [06:13<00:27, 1.46it/s]\n 80%|████████ | 161/200 [06:13<00:20, 1.92it/s]\n 81%|████████ | 162/200 [06:13<00:18, 2.10it/s]\n 82%|████████▏ | 163/200 [06:17<00:52, 1.42s/it]\n 82%|████████▏ | 164/200 [06:21<01:15, 2.10s/it]\n 82%|████████▎ | 165/200 [06:21<00:54, 1.55s/it]\n 83%|████████▎ | 166/200 [06:25<01:12, 2.15s/it]\n 84%|████████▎ | 167/200 [06:28<01:24, 2.57s/it]\n 84%|████████▍ | 168/200 [06:28<01:00, 1.89s/it]\n 84%|████████▍ | 169/200 [06:29<00:43, 1.41s/it]\n 85%|████████▌ | 170/200 [06:29<00:32, 1.08s/it]\n 86%|████████▌ | 171/200 [06:33<00:53, 1.84s/it]\n 86%|████████▌ | 172/200 [06:36<01:06, 2.39s/it]\n 86%|████████▋ | 173/200 [06:40<01:17, 2.86s/it]\n 87%|████████▋ | 174/200 [06:44<01:19, 3.07s/it]\n 88%|████████▊ | 175/200 [06:44<00:54, 2.19s/it]\n 88%|████████▊ | 176/200 [06:48<01:03, 2.65s/it]\n 88%|████████▊ | 177/200 [06:51<01:08, 2.98s/it]\n 89%|████████▉ | 178/200 [06:55<01:10, 3.19s/it]\n 90%|████████▉ | 179/200 [06:55<00:47, 2.28s/it]\n 90%|█████████ | 180/200 [06:56<00:34, 1.70s/it]\n 90%|█████████ | 181/200 [06:56<00:24, 1.31s/it]\n 91%|█████████ | 182/200 [07:00<00:37, 2.09s/it]\n 92%|█████████▏| 183/200 [07:04<00:43, 2.57s/it]\n 92%|█████████▏| 184/200 [07:04<00:29, 1.87s/it]\n 92%|█████████▎| 185/200 [07:04<00:21, 1.40s/it]\n 93%|█████████▎| 186/200 [07:08<00:28, 2.06s/it]\n 94%|█████████▎| 187/200 [07:08<00:19, 1.52s/it]\n 94%|█████████▍| 188/200 [07:08<00:13, 1.15s/it]\n 94%|█████████▍| 189/200 [07:09<00:09, 1.10it/s]\n 95%|█████████▌| 190/200 [07:12<00:17, 1.73s/it]\n 96%|█████████▌| 191/200 [07:13<00:11, 1.29s/it]\n 96%|█████████▌| 192/200 [07:13<00:07, 1.00it/s]\n 96%|█████████▋| 193/200 [07:17<00:12, 1.80s/it]\n 97%|█████████▋| 194/200 [07:20<00:14, 2.36s/it]\n 98%|█████████▊| 195/200 [07:21<00:08, 1.75s/it]\n 98%|█████████▊| 196/200 [07:24<00:09, 2.36s/it]\n 98%|█████████▊| 197/200 [07:25<00:05, 1.75s/it]\n 99%|█████████▉| 198/200 [07:25<00:02, 1.33s/it]\n100%|█████████▉| 199/200 [07:29<00:02, 2.01s/it]\n100%|██████████| 200/200 [07:32<00:00, 2.50s/it]\n100%|██████████| 200/200 [07:32<00:00, 2.26s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752093627/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_1752093627/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_1752093627/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_1752093627/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 (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 : 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 : 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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 (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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 452.75040316581726\nerrors 81\nmean length: 1.785\n\nthroughput (request / second): 0.44174449895906803\nthroughput (character / second): 0.7885139306419364\naverage request duration (s) 2.26361963391304\n50%ile request duration (s) 3.532205581665039\n75%ile request duration (s) 3.6526861786842346\n90%ile request duration (s) 3.7241708993911744\n95%ile request duration (s) 3.777702105045319\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v3-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-76584-v3-profiler
Service chaiml-llama3-200m-v2-t-76584-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.72s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v3-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.54s
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-llama3-200m-v2-t-76584-v3-profiler
Waiting for inference service chaiml-llama3-200m-v2-t-76584-v3-profiler to be ready
Inference service chaiml-llama3-200m-v2-t-76584-v3-profiler ready after 50.67388987541199s
Pipeline stage MKMLProfilerDeployer completed in 51.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q:/code/chaiverse_profiler_1752094212 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752094212 && 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_1752094212/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q:/code/chaiverse_profiler_1752094650 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752094650 && 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_1752094650/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q:/code/chaiverse_profiler_1752095100 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama3-200m-v674b802f26407d125d7cc694c3cc02c2-deplovq48q --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752095100 && 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_1752095100/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<11:49, 3.56s/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 [00:07<04:14, 1.30s/it]\n 2%|▎ | 5/200 [00:07<02:59, 1.09it/s]\n 3%|▎ | 6/200 [00:11<05:44, 1.78s/it]\n 4%|▎ | 7/200 [00:11<04:07, 1.28s/it]\n 4%|▍ | 8/200 [00:11<03:03, 1.05it/s]\n 4%|▍ | 9/200 [00:15<05:31, 1.74s/it]\n 5%|▌ | 10/200 [00:15<04:01, 1.27s/it]\n 6%|▌ | 11/200 [00:15<03:03, 1.03it/s]\n 6%|▌ | 12/200 [00:15<02:23, 1.31it/s]\n 6%|▋ | 13/200 [00:19<04:56, 1.59s/it]\n 7%|▋ | 14/200 [00:22<06:43, 2.17s/it]\n 8%|▊ | 15/200 [00:26<07:54, 2.56s/it]\n 8%|▊ | 16/200 [00:26<05:46, 1.88s/it]\n 8%|▊ | 17/200 [00:30<07:12, 2.37s/it]\n 9%|▉ | 18/200 [00:33<08:09, 2.69s/it]\n 10%|▉ | 19/200 [00:37<08:45, 2.90s/it]\n 10%|█ | 20/200 [00:37<06:13, 2.07s/it]\n 10%|█ | 21/200 [00:37<04:34, 1.53s/it]\n 11%|█ | 22/200 [00:37<03:25, 1.16s/it]\n 12%|█▏ | 23/200 [00:37<02:38, 1.12it/s]\n 12%|█▏ | 24/200 [00:38<02:04, 1.42it/s]\n 12%|█▎ | 25/200 [00:41<04:27, 1.53s/it]\n 13%|█▎ | 26/200 [00:45<06:07, 2.11s/it]\n 14%|█▎ | 27/200 [00:45<04:28, 1.55s/it]\n 14%|█▍ | 28/200 [00:45<03:20, 1.17s/it]\n 14%|█▍ | 29/200 [00:45<02:33, 1.11it/s]\n 15%|█▌ | 30/200 [00:46<01:53, 1.50it/s]\n 16%|█▌ | 31/200 [00:49<04:24, 1.56s/it]\n 16%|█▌ | 32/200 [00:49<03:11, 1.14s/it]\n 16%|█▋ | 33/200 [00:53<05:13, 1.88s/it]\n 17%|█▋ | 34/200 [00:53<03:44, 1.35s/it]\n 18%|█▊ | 35/200 [00:57<05:28, 1.99s/it]\n 18%|█▊ | 36/200 [01:00<06:45, 2.47s/it]\n 18%|█▊ | 37/200 [01:00<04:48, 1.77s/it]\n 19%|█▉ | 38/200 [01:04<06:10, 2.29s/it]\n 20%|█▉ | 39/200 [01:07<07:07, 2.66s/it]\n 20%|██ | 40/200 [01:11<07:46, 2.92s/it]\n 20%|██ | 41/200 [01:11<05:31, 2.08s/it]\n 21%|██ | 42/200 [01:15<06:41, 2.54s/it]\n 22%|██▏ | 43/200 [01:18<07:22, 2.82s/it]\n 22%|██▏ | 44/200 [01:18<05:13, 2.01s/it]\n 22%|██▎ | 45/200 [01:22<06:25, 2.48s/it]\n 23%|██▎ | 46/200 [01:22<04:33, 1.78s/it]\n 24%|██▎ | 47/200 [01:22<03:23, 1.33s/it]\n 24%|██▍ | 48/200 [01:26<05:02, 1.99s/it]\n 24%|██▍ | 49/200 [01:26<03:40, 1.46s/it]\n 25%|██▌ | 50/200 [01:29<05:09, 2.06s/it]\n 26%|██▌ | 51/200 [01:33<06:11, 2.49s/it]\n 26%|██▌ | 52/200 [01:36<06:56, 2.81s/it]\n 26%|██▋ | 53/200 [01:37<04:54, 2.01s/it]\n 27%|██▋ | 54/200 [01:37<03:36, 1.48s/it]\n 28%|██▊ | 55/200 [01:37<02:41, 1.11s/it]\n 28%|██▊ | 56/200 [01:41<04:21, 1.82s/it]\n 28%|██▊ | 57/200 [01:44<05:29, 2.31s/it]\n 29%|██▉ | 58/200 [01:44<03:59, 1.69s/it]\n 30%|██▉ | 59/200 [01:45<02:57, 1.26s/it]\n 30%|███ | 60/200 [01:45<02:14, 1.04it/s]\n 30%|███ | 61/200 [01:48<03:58, 1.72s/it]\n 31%|███ | 62/200 [01:52<05:06, 2.22s/it]\n 32%|███▏ | 63/200 [01:55<05:55, 2.60s/it]\n 32%|███▏ | 64/200 [01:59<06:28, 2.86s/it]\n 32%|███▎ | 65/200 [02:02<06:51, 3.05s/it]\n 33%|███▎ | 66/200 [02:02<04:51, 2.18s/it]\n 34%|███▎ | 67/200 [02:03<03:33, 1.60s/it]\n 34%|███▍ | 68/200 [02:03<02:39, 1.21s/it]\n 34%|███▍ | 69/200 [02:06<04:07, 1.89s/it]\n 35%|███▌ | 70/200 [02:10<05:06, 2.35s/it]\n 36%|███▌ | 71/200 [02:13<05:48, 2.71s/it]\n 36%|███▌ | 72/200 [02:17<06:08, 2.88s/it]\n 36%|███▋ | 73/200 [02:20<06:31, 3.08s/it]\n 37%|███▋ | 74/200 [02:20<04:36, 2.20s/it]\n 38%|███▊ | 75/200 [02:20<03:21, 1.61s/it]\n 38%|███▊ | 76/200 [02:21<02:29, 1.21s/it]\n 38%|███▊ | 77/200 [02:24<03:54, 1.91s/it]\n 39%|███▉ | 78/200 [02:28<04:45, 2.34s/it]\n 40%|███▉ | 79/200 [02:31<05:28, 2.72s/it]\n 40%|████ | 80/200 [02:31<03:52, 1.94s/it]\n 40%|████ | 81/200 [02:35<04:46, 2.41s/it]\n 41%|████ | 82/200 [02:38<05:24, 2.75s/it]\n 42%|████▏ | 83/200 [02:42<05:47, 2.97s/it]\n 42%|████▏ | 84/200 [02:42<04:06, 2.12s/it]\n 42%|████▎ | 85/200 [02:46<04:55, 2.57s/it]\n 43%|████▎ | 86/200 [02:49<05:19, 2.80s/it]\n 44%|████▎ | 87/200 [02:53<05:42, 3.03s/it]\n 44%|████▍ | 88/200 [02:53<04:01, 2.16s/it]\n 44%|████▍ | 89/200 [02:53<02:56, 1.59s/it]\n 45%|████▌ | 90/200 [02:53<02:10, 1.19s/it]\n 46%|████▌ | 91/200 [02:53<01:39, 1.09it/s]\n 46%|████▌ | 92/200 [02:57<03:03, 1.70s/it]\n 46%|████▋ | 93/200 [03:01<04:03, 2.27s/it]\n 47%|████▋ | 94/200 [03:04<04:37, 2.62s/it]\n 48%|████▊ | 95/200 [03:04<03:21, 1.92s/it]\n 48%|████▊ | 96/200 [03:08<04:09, 2.40s/it]\n 48%|████▊ | 97/200 [03:11<04:39, 2.71s/it]\n 49%|████▉ | 98/200 [03:15<05:00, 2.94s/it]\n 50%|████▉ | 99/200 [03:15<03:36, 2.15s/it]\n 50%|█████ | 100/200 [03:19<04:15, 2.56s/it]\n 50%|█████ | 101/200 [03:19<03:04, 1.87s/it]\n 51%|█████ | 102/200 [03:19<02:16, 1.39s/it]\n 52%|█████▏ | 103/200 [03:23<03:15, 2.02s/it]\n 52%|█████▏ | 104/200 [03:26<03:54, 2.44s/it]\n 52%|█████▎ | 105/200 [03:26<02:45, 1.74s/it]\n 53%|█████▎ | 106/200 [03:26<02:02, 1.30s/it]\n 54%|█████▎ | 107/200 [03:27<01:32, 1.01it/s]\n 54%|█████▍ | 108/200 [03:27<01:11, 1.28it/s]\n 55%|█████▍ | 109/200 [03:30<02:24, 1.59s/it]\n 55%|█████▌ | 110/200 [03:34<03:13, 2.15s/it]\n 56%|█████▌ | 111/200 [03:34<02:20, 1.57s/it]\n 56%|█████▌ | 112/200 [03:38<03:08, 2.14s/it]\n 56%|█████▋ | 113/200 [03:41<03:43, 2.56s/it]\n 57%|█████▋ | 114/200 [03:45<04:06, 2.87s/it]\n 57%|█████▊ | 115/200 [03:48<04:16, 3.02s/it]\n 58%|█████▊ | 116/200 [03:52<04:25, 3.16s/it]\n 58%|█████▊ | 117/200 [03:52<03:07, 2.25s/it]\n 59%|█████▉ | 118/200 [03:55<03:36, 2.63s/it]\n 60%|█████▉ | 119/200 [03:59<03:54, 2.90s/it]\n 60%|██████ | 120/200 [04:03<04:12, 3.16s/it]\n 60%|██████ | 121/200 [04:03<02:57, 2.25s/it]\n 61%|██████ | 122/200 [04:06<03:26, 2.65s/it]\n 62%|██████▏ | 123/200 [04:06<02:26, 1.90s/it]\n 62%|██████▏ | 124/200 [04:10<03:01, 2.39s/it]\n 62%|██████▎ | 125/200 [04:14<03:28, 2.77s/it]\n 63%|██████▎ | 126/200 [04:14<02:26, 1.98s/it]\n 64%|██████▎ | 127/200 [04:14<01:47, 1.47s/it]\n 64%|██████▍ | 128/200 [04:14<01:19, 1.11s/it]\n 64%|██████▍ | 129/200 [04:18<02:10, 1.84s/it]\n 65%|██████▌ | 130/200 [04:18<01:35, 1.36s/it]\n 66%|██████▌ | 131/200 [04:22<02:17, 2.00s/it]\n 66%|██████▌ | 132/200 [04:25<02:46, 2.45s/it]\n 66%|██████▋ | 133/200 [04:28<03:04, 2.75s/it]\n 67%|██████▋ | 134/200 [04:32<03:16, 2.98s/it]\n 68%|██████▊ | 135/200 [04:35<03:22, 3.12s/it]\n 68%|██████▊ | 136/200 [04:39<03:26, 3.23s/it]\n 68%|██████▊ | 137/200 [04:42<03:28, 3.31s/it]\n 69%|██████▉ | 138/200 [04:43<02:28, 2.39s/it]\n 70%|██████▉ | 139/200 [04:43<01:47, 1.77s/it]\n 70%|███████ | 140/200 [04:46<02:15, 2.26s/it]\n 70%|███████ | 141/200 [04:50<02:34, 2.62s/it]\n 71%|███████ | 142/200 [04:53<02:47, 2.89s/it]\n 72%|███████▏ | 143/200 [04:54<01:59, 2.10s/it]\n 72%|███████▏ | 144/200 [04:57<02:22, 2.54s/it]\n 72%|███████▎ | 145/200 [04:57<01:41, 1.85s/it]\n 73%|███████▎ | 146/200 [04:58<01:14, 1.38s/it]\n 74%|███████▎ | 147/200 [04:58<00:55, 1.05s/it]\n 74%|███████▍ | 148/200 [05:01<01:32, 1.77s/it]\n 74%|███████▍ | 149/200 [05:05<01:55, 2.26s/it]\n 75%|███████▌ | 150/200 [05:08<02:12, 2.65s/it]\n 76%|███████▌ | 151/200 [05:12<02:22, 2.91s/it]\n 76%|███████▌ | 152/200 [05:15<02:28, 3.09s/it]\n 76%|███████▋ | 153/200 [05:16<01:43, 2.20s/it]\n 77%|███████▋ | 154/200 [05:16<01:14, 1.63s/it]\n 78%|███████▊ | 155/200 [05:19<01:38, 2.19s/it]\n 78%|███████▊ | 156/200 [05:20<01:10, 1.61s/it]\n 78%|███████▊ | 157/200 [05:23<01:32, 2.16s/it]\n 79%|███████▉ | 158/200 [05:27<01:47, 2.55s/it]\n 80%|███████▉ | 159/200 [05:30<01:57, 2.85s/it]\n 80%|████████ | 160/200 [05:30<01:21, 2.04s/it]\n 80%|████████ | 161/200 [05:31<00:59, 1.51s/it]\n 81%|████████ | 162/200 [05:34<01:20, 2.12s/it]\n 82%|████████▏ | 163/200 [05:34<00:57, 1.57s/it]\n 82%|████████▏ | 164/200 [05:38<01:18, 2.17s/it]\n 82%|████████▎ | 165/200 [05:42<01:31, 2.60s/it]\n 83%|████████▎ | 166/200 [05:45<01:37, 2.87s/it]\n 84%|████████▎ | 167/200 [05:48<01:40, 3.05s/it]\n 84%|████████▍ | 168/200 [05:52<01:42, 3.19s/it]\n 84%|████████▍ | 169/200 [05:52<01:10, 2.27s/it]\n 85%|████████▌ | 170/200 [05:56<01:18, 2.63s/it]\n 86%|████████▌ | 171/200 [05:59<01:24, 2.91s/it]\n 86%|████████▌ | 172/200 [05:59<00:58, 2.08s/it]\n 86%|████████▋ | 173/200 [06:03<01:08, 2.55s/it]\n 87%|████████▋ | 174/200 [06:06<01:13, 2.82s/it]\n 88%|████████▊ | 175/200 [06:10<01:15, 3.01s/it]\n 88%|████████▊ | 176/200 [06:10<00:52, 2.18s/it]\n 88%|████████▊ | 177/200 [06:14<00:59, 2.57s/it]\n 89%|████████▉ | 178/200 [06:14<00:41, 1.87s/it]\n 90%|████████▉ | 179/200 [06:17<00:49, 2.36s/it]\n 90%|█████████ | 180/200 [06:21<00:54, 2.73s/it]\n 90%|█████████ | 181/200 [06:21<00:37, 1.95s/it]\n 91%|█████████ | 182/200 [06:21<00:26, 1.45s/it]\n 92%|█████████▏| 183/200 [06:22<00:18, 1.10s/it]\n 92%|█████████▏| 184/200 [06:22<00:13, 1.17it/s]\n 92%|█████████▎| 185/200 [06:25<00:24, 1.64s/it]\n 93%|█████████▎| 186/200 [06:26<00:17, 1.22s/it]\n 94%|█████████▎| 187/200 [06:29<00:24, 1.90s/it]\n 94%|█████████▍| 188/200 [06:29<00:16, 1.41s/it]\n 94%|█████████▍| 189/200 [06:30<00:11, 1.07s/it]\n 95%|█████████▌| 190/200 [06:30<00:08, 1.20it/s]\n 96%|█████████▌| 191/200 [06:30<00:05, 1.51it/s]\n 96%|█████████▌| 192/200 [06:30<00:04, 2.00it/s]\n 96%|█████████▋| 193/200 [06:31<00:03, 2.32it/s]\n 97%|█████████▋| 194/200 [06:31<00:02, 2.64it/s]\n 98%|█████████▊| 195/200 [06:34<00:06, 1.30s/it]\n 98%|█████████▊| 196/200 [06:38<00:07, 1.93s/it]\n 98%|█████████▊| 197/200 [06:38<00:04, 1.43s/it]\n 99%|█████████▉| 198/200 [06:38<00:02, 1.08s/it]\n100%|█████████▉| 199/200 [06:38<00:00, 1.19it/s]\n100%|██████████| 200/200 [06:42<00:00, 1.63s/it]\n100%|██████████| 200/200 [06:42<00:00, 2.01s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752095100/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_1752095100/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_1752095100/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_1752095100/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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 402.4392578601837\nerrors 91\nmean length: 1.635\n\nthroughput (request / second): 0.49696940865914335\nthroughput (character / second): 0.8125449831576993\naverage request duration (s) 2.0120825564861295\n50%ile request duration (s) 3.4176321029663086\n75%ile request duration (s) 3.498158872127533\n90%ile request duration (s) 3.562061882019043\n95%ile request duration (s) 3.588810670375824\n\nmean input tokens 2.0\nmean output tokens 1.0\n\n\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama3-200m-v2-t-76584-v3-profiler is running
Tearing down inference service chaiml-llama3-200m-v2-t-76584-v3-profiler
Service chaiml-llama3-200m-v2-t-76584-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.74s
Shutdown handler de-registered
chaiml-llama3-200m-v2-t_76584_v3 status is now inactive due to auto deactivation removed underperforming models
Failed to get response for submission zmeeks-capitanito-54-3000_v3: HTTPConnectionPool(host='zmeeks-capitanito-54-3000-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama3-200m-v2-t_76584_v3 status is now torndown due to DeploymentManager action