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-nis-8b-v1-llama3-48598-v5-mkmlizer
Waiting for job on chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer to finish
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Version: 0.29.15 ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ belonging to: ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ║ ║
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: Downloaded to shared memory in 16.256s
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: Checking if ChaiML/nis-8b-v1-llama3-try3-new8m-1Mhighdistil-512seqv2-kdw02-acc576 already exists in ChaiML
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpmct6xm9z, device:0
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: quantized model in 18.931s
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: Processed model ChaiML/nis-8b-v1-llama3-try3-new8m-1Mhighdistil-512seqv2-kdw02-acc576 in 35.188s
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia/config.json
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia/special_tokens_map.json
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia/tokenizer_config.json
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia/tokenizer.json
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-8b-v1-llama3-48598-v5/nvidia/flywheel_model.0.safetensors
chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 38.71it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 58.12it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 48.77it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:05, 51.01it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:04, 52.66it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 47.48it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 46.93it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 52.68it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 46.14it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 44.99it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 49.92it/s]
Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 46.61it/s]
Loading 0: 27%|██▋ | 78/291 [00:01<00:04, 46.39it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:06, 33.41it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:06, 32.57it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:04, 40.10it/s]
Loading 0: 34%|███▍ | 100/291 [00:02<00:04, 40.12it/s]
Loading 0: 36%|███▌ | 105/291 [00:02<00:04, 41.14it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 47.45it/s]
Loading 0: 41%|████ | 118/291 [00:02<00:03, 44.49it/s]
Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 43.73it/s]
Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 48.35it/s]
Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 44.81it/s]
Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 45.14it/s]
Loading 0: 51%|█████ | 148/291 [00:03<00:02, 50.35it/s]
Loading 0: 53%|█████▎ | 154/291 [00:03<00:02, 46.94it/s]
Loading 0: 55%|█████▍ | 159/291 [00:03<00:02, 46.79it/s]
Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 51.69it/s]
Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.43it/s]
Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 49.86it/s]
Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 50.45it/s]
Loading 0: 66%|██████▌ | 191/291 [00:04<00:03, 32.91it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 34.03it/s]
Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 37.19it/s]
Loading 0: 71%|███████ | 206/291 [00:04<00:02, 38.91it/s]
Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 39.65it/s]
Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 39.58it/s]
Loading 0: 76%|███████▋ | 222/291 [00:05<00:01, 40.26it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 46.46it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 44.18it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 43.51it/s]
Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 49.05it/s]
Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 46.15it/s]
Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 45.27it/s]
Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 50.45it/s]
Loading 0: 93%|█████████▎| 271/291 [00:06<00:00, 46.97it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 45.34it/s]
Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 45.31it/s]
Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 40.79it/s]
Loading 0: 100%|██████████| 291/291 [00:06<00:00, 32.51it/s]
Job chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer completed after 54.64s with status: succeeded
Stopping job with name chaiml-nis-8b-v1-llama3-48598-v5-mkmlizer
Pipeline stage MKMLizer completed in 55.15s
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-nis-8b-v1-llama3-48598-v5
Waiting for inference service chaiml-nis-8b-v1-llama3-48598-v5 to be ready
Inference service chaiml-nis-8b-v1-llama3-48598-v5 ready after 321.20081901550293s
Pipeline stage MKMLDeployer completed in 321.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.236266136169434s
Received healthy response to inference request in 2.0390849113464355s
Received healthy response to inference request in 3.45045804977417s
Received healthy response to inference request in 3.931018352508545s
Received healthy response to inference request in 2.5411460399627686s
5 requests
0 failed requests
5th percentile: 2.1394971370697022
10th percentile: 2.239909362792969
20th percentile: 2.440733814239502
30th percentile: 2.7230084419250487
40th percentile: 3.0867332458496093
50th percentile: 3.45045804977417
60th percentile: 3.64268217086792
70th percentile: 3.8349062919616697
80th percentile: 4.392067909240723
90th percentile: 5.314167022705078
95th percentile: 5.775216579437256
99th percentile: 6.144056224822998
mean time: 3.6395946979522704
Pipeline stage StressChecker completed in 19.51s
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 0.75s
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 0.68s
Shutdown handler de-registered
chaiml-nis-8b-v1-llama3_48598_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%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-nis-8b-v1-llama3-48598-v5-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 5.47s
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-nis-8b-v1-llama3-48598-v5-profiler
Waiting for inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler to be ready
Inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler ready after 333.19887590408325s
Pipeline stage MKMLProfilerDeployer completed in 333.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6:/code/chaiverse_profiler_1752877823 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752877823 && 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_1752877823/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6:/code/chaiverse_profiler_1752878240 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752878240 && 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_1752878240/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6:/code/chaiverse_profiler_1752878667 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deplodzvv6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752878667 && 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_1752878667/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<00:31, 6.34it/s]\n 1%| | 2/200 [00:03<07:19, 2.22s/it]\n 2%|▏ | 3/200 [00:07<09:12, 2.80s/it]\n 2%|▏ | 4/200 [00:07<05:43, 1.75s/it]\n 2%|▎ | 5/200 [00:07<03:56, 1.21s/it]\n 3%|▎ | 6/200 [00:11<06:34, 2.03s/it]\n 4%|▎ | 7/200 [00:11<04:41, 1.46s/it]\n 4%|▍ | 8/200 [00:11<03:27, 1.08s/it]\n 4%|▍ | 9/200 [00:15<05:51, 1.84s/it]\n 5%|▌ | 10/200 [00:15<04:17, 1.35s/it]\n 6%|▌ | 11/200 [00:19<06:22, 2.03s/it]\n 6%|▌ | 12/200 [00:19<04:40, 1.49s/it]\n 6%|▋ | 13/200 [00:19<03:29, 1.12s/it]\n 7%|▋ | 14/200 [00:20<02:40, 1.16it/s]\n 8%|▊ | 15/200 [00:23<05:08, 1.67s/it]\n 8%|▊ | 16/200 [00:23<03:52, 1.27s/it]\n 8%|▊ | 17/200 [00:27<06:00, 1.97s/it]\n 9%|▉ | 18/200 [00:31<07:32, 2.48s/it]\n 10%|▉ | 19/200 [00:34<08:20, 2.77s/it]\n 10%|█ | 20/200 [00:38<09:05, 3.03s/it]\n 10%|█ | 21/200 [00:41<09:22, 3.14s/it]\n 11%|█ | 22/200 [00:41<06:47, 2.29s/it]\n 12%|█▏ | 23/200 [00:42<04:59, 1.69s/it]\n 12%|█▏ | 24/200 [00:42<03:44, 1.27s/it]\n 12%|█▎ | 25/200 [00:42<02:50, 1.03it/s]\n 13%|█▎ | 26/200 [00:43<02:13, 1.30it/s]\n 14%|█▎ | 27/200 [00:46<04:34, 1.59s/it]\n 14%|█▍ | 28/200 [00:50<06:14, 2.18s/it]\n 14%|█▍ | 29/200 [00:53<07:18, 2.57s/it]\n 15%|█▌ | 30/200 [00:53<05:18, 1.87s/it]\n 16%|█▌ | 31/200 [00:57<06:43, 2.39s/it]\n 16%|█▌ | 32/200 [01:01<07:42, 2.76s/it]\n 16%|█▋ | 33/200 [01:01<05:34, 2.01s/it]\n 17%|█▋ | 34/200 [01:01<04:07, 1.49s/it]\n 18%|█▊ | 35/200 [01:01<03:06, 1.13s/it]\n 18%|█▊ | 36/200 [01:05<05:01, 1.84s/it]\n 18%|█▊ | 37/200 [01:05<03:36, 1.33s/it]\n 19%|█▉ | 38/200 [01:05<02:45, 1.02s/it]\n 20%|█▉ | 39/200 [01:09<04:54, 1.83s/it]\n 20%|██ | 40/200 [01:09<03:31, 1.32s/it]\n 20%|██ | 41/200 [01:13<05:21, 2.02s/it]\n 21%|██ | 42/200 [01:13<03:50, 1.46s/it]\n 22%|██▏ | 43/200 [01:13<02:54, 1.11s/it]\n 22%|██▏ | 44/200 [01:17<04:46, 1.84s/it]\n 22%|██▎ | 45/200 [01:17<03:31, 1.36s/it]\n 23%|██▎ | 46/200 [01:21<05:12, 2.03s/it]\n 24%|██▎ | 47/200 [01:21<03:49, 1.50s/it]\n 24%|██▍ | 48/200 [01:24<05:14, 2.07s/it]\n 24%|██▍ | 49/200 [01:28<06:23, 2.54s/it]\n 25%|██▌ | 50/200 [01:28<04:32, 1.82s/it]\n 26%|██▌ | 51/200 [01:28<03:21, 1.35s/it]\n 26%|██▌ | 52/200 [01:32<05:01, 2.04s/it]\n 26%|██▋ | 53/200 [01:36<06:09, 2.52s/it]\n 27%|██▋ | 54/200 [01:39<06:52, 2.83s/it]\n 28%|██▊ | 55/200 [01:43<07:15, 3.00s/it]\n 28%|██▊ | 56/200 [01:43<05:08, 2.14s/it]\n 28%|██▊ | 57/200 [01:43<03:45, 1.57s/it]\n 29%|██▉ | 58/200 [01:47<05:08, 2.17s/it]\n 30%|██▉ | 59/200 [01:50<06:01, 2.56s/it]\n 30%|███ | 60/200 [01:50<04:21, 1.87s/it]\n 30%|███ | 61/200 [01:54<05:40, 2.45s/it]\n 31%|███ | 62/200 [01:58<06:23, 2.78s/it]\n 32%|███▏ | 63/200 [02:01<06:50, 3.00s/it]\n 32%|███▏ | 64/200 [02:01<04:50, 2.13s/it]\n 32%|███▎ | 65/200 [02:02<03:32, 1.57s/it]\n 33%|███▎ | 66/200 [02:05<04:52, 2.18s/it]\n 34%|███▎ | 67/200 [02:09<05:43, 2.58s/it]\n 34%|███▍ | 68/200 [02:09<04:10, 1.90s/it]\n 34%|███▍ | 69/200 [02:12<05:12, 2.38s/it]\n 35%|███▌ | 70/200 [02:16<05:56, 2.74s/it]\n 36%|███▌ | 71/200 [02:16<04:13, 1.96s/it]\n 36%|███▌ | 72/200 [02:20<05:15, 2.47s/it]\n 36%|███▋ | 73/200 [02:20<03:50, 1.81s/it]\n 37%|███▋ | 74/200 [02:24<04:58, 2.37s/it]\n 38%|███▊ | 75/200 [02:28<05:47, 2.78s/it]\n 38%|███▊ | 76/200 [02:28<04:06, 1.99s/it]\n 38%|███▊ | 77/200 [02:31<05:05, 2.49s/it]\n 39%|███▉ | 78/200 [02:32<03:42, 1.82s/it]\n 40%|███▉ | 79/200 [02:35<04:45, 2.36s/it]\n 40%|████ | 80/200 [02:39<05:21, 2.68s/it]\n 40%|████ | 81/200 [02:42<05:52, 2.96s/it]\n 41%|████ | 82/200 [02:42<04:09, 2.11s/it]\n 42%|████▏ | 83/200 [02:43<03:03, 1.57s/it]\n 42%|████▏ | 84/200 [02:46<04:06, 2.12s/it]\n 42%|████▎ | 85/200 [02:46<03:00, 1.57s/it]\n 43%|████▎ | 86/200 [02:50<04:07, 2.17s/it]\n 44%|████▎ | 87/200 [02:50<03:01, 1.60s/it]\n 44%|████▍ | 88/200 [02:50<02:14, 1.20s/it]\n 44%|████▍ | 89/200 [02:51<01:41, 1.09it/s]\n 45%|████▌ | 90/200 [02:51<01:19, 1.39it/s]\n 46%|████▌ | 91/200 [02:55<02:53, 1.59s/it]\n 46%|████▌ | 92/200 [02:55<02:09, 1.20s/it]\n 46%|████▋ | 93/200 [02:58<03:24, 1.91s/it]\n 47%|████▋ | 94/200 [03:02<04:13, 2.39s/it]\n 48%|████▊ | 95/200 [03:02<03:04, 1.75s/it]\n 48%|████▊ | 96/200 [03:03<02:15, 1.30s/it]\n 48%|████▊ | 97/200 [03:06<03:21, 1.96s/it]\n 49%|████▉ | 98/200 [03:10<04:08, 2.44s/it]\n 50%|████▉ | 99/200 [03:10<03:00, 1.79s/it]\n 50%|█████ | 100/200 [03:10<02:13, 1.33s/it]\n 50%|█████ | 101/200 [03:10<01:40, 1.01s/it]\n 51%|█████ | 102/200 [03:11<01:17, 1.26it/s]\n 52%|█████▏ | 103/200 [03:11<00:57, 1.68it/s]\n 52%|█████▏ | 104/200 [03:14<02:25, 1.51s/it]\n 52%|█████▎ | 105/200 [03:15<01:48, 1.14s/it]\n 53%|█████▎ | 106/200 [03:18<02:52, 1.84s/it]\n 54%|█████▎ | 107/200 [03:18<02:06, 1.36s/it]\n 54%|█████▍ | 108/200 [03:22<03:07, 2.03s/it]\n 55%|█████▍ | 109/200 [03:26<03:49, 2.53s/it]\n 55%|█████▌ | 110/200 [03:29<04:13, 2.82s/it]\n 56%|█████▌ | 111/200 [03:29<02:59, 2.02s/it]\n 56%|█████▌ | 112/200 [03:33<03:41, 2.52s/it]\n 56%|█████▋ | 113/200 [03:33<02:37, 1.81s/it]\n 57%|█████▋ | 114/200 [03:33<01:55, 1.35s/it]\n 57%|█████▊ | 115/200 [03:34<01:26, 1.02s/it]\n 58%|█████▊ | 116/200 [03:34<01:06, 1.26it/s]\n 58%|█████▊ | 117/200 [03:34<00:52, 1.57it/s]\n 59%|█████▉ | 118/200 [03:34<00:42, 1.92it/s]\n 60%|█████▉ | 119/200 [03:38<01:55, 1.42s/it]\n 60%|██████ | 120/200 [03:42<02:46, 2.09s/it]\n 60%|██████ | 121/200 [03:45<03:20, 2.54s/it]\n 61%|██████ | 122/200 [03:49<03:40, 2.83s/it]\n 62%|██████▏ | 123/200 [03:49<02:39, 2.07s/it]\n 62%|██████▏ | 124/200 [03:49<01:56, 1.54s/it]\n 62%|██████▎ | 125/200 [03:53<02:41, 2.16s/it]\n 63%|██████▎ | 126/200 [03:57<03:11, 2.59s/it]\n 64%|██████▎ | 127/200 [04:00<03:31, 2.89s/it]\n 64%|██████▍ | 128/200 [04:00<02:28, 2.07s/it]\n 64%|██████▍ | 129/200 [04:01<01:49, 1.55s/it]\n 65%|██████▌ | 130/200 [04:01<01:21, 1.17s/it]\n 66%|██████▌ | 131/200 [04:05<02:11, 1.90s/it]\n 66%|██████▌ | 132/200 [04:05<01:35, 1.41s/it]\n 66%|██████▋ | 133/200 [04:08<02:15, 2.03s/it]\n 67%|██████▋ | 134/200 [04:12<02:44, 2.49s/it]\n 68%|██████▊ | 135/200 [04:12<01:58, 1.83s/it]\n 68%|██████▊ | 136/200 [04:12<01:27, 1.37s/it]\n 68%|██████▊ | 137/200 [04:13<01:06, 1.05s/it]\n 69%|██████▉ | 138/200 [04:13<00:50, 1.22it/s]\n 70%|██████▉ | 139/200 [04:13<00:40, 1.51it/s]\n 70%|███████ | 140/200 [04:17<01:32, 1.54s/it]\n 70%|███████ | 141/200 [04:20<02:07, 2.16s/it]\n 71%|███████ | 142/200 [04:21<01:30, 1.55s/it]\n 72%|███████▏ | 143/200 [04:21<01:06, 1.17s/it]\n 72%|███████▏ | 144/200 [04:24<01:45, 1.89s/it]\n 72%|███████▎ | 145/200 [04:28<02:14, 2.44s/it]\n 73%|███████▎ | 146/200 [04:28<01:34, 1.76s/it]\n 74%|███████▎ | 147/200 [04:29<01:10, 1.32s/it]\n 74%|███████▍ | 148/200 [04:32<01:42, 1.98s/it]\n 74%|███████▍ | 149/200 [04:32<01:15, 1.48s/it]\n 75%|███████▌ | 150/200 [04:33<00:56, 1.13s/it]\n 76%|███████▌ | 151/200 [04:33<00:43, 1.12it/s]\n 76%|███████▌ | 152/200 [04:37<01:19, 1.66s/it]\n 76%|███████▋ | 153/200 [04:40<01:42, 2.18s/it]\n 77%|███████▋ | 154/200 [04:40<01:13, 1.60s/it]\n 78%|███████▊ | 155/200 [04:44<01:40, 2.23s/it]\n 78%|███████▊ | 156/200 [04:47<01:55, 2.63s/it]\n 78%|███████▊ | 157/200 [04:51<02:04, 2.90s/it]\n 79%|███████▉ | 158/200 [04:51<01:27, 2.07s/it]\n 80%|███████▉ | 159/200 [04:51<01:02, 1.53s/it]\n 80%|████████ | 160/200 [04:55<01:24, 2.11s/it]\n 80%|████████ | 161/200 [04:59<01:40, 2.58s/it]\n 81%|████████ | 162/200 [05:02<01:48, 2.85s/it]\n 82%|████████▏ | 163/200 [05:02<01:15, 2.03s/it]\n 82%|████████▏ | 164/200 [05:06<01:31, 2.54s/it]\n 82%|████████▎ | 165/200 [05:09<01:37, 2.78s/it]\n 83%|████████▎ | 166/200 [05:09<01:07, 1.98s/it]\n 84%|████████▎ | 167/200 [05:13<01:21, 2.46s/it]\n 84%|████████▍ | 168/200 [05:17<01:29, 2.81s/it]\n 84%|████████▍ | 169/200 [05:20<01:33, 3.01s/it]\n 85%|████████▌ | 170/200 [05:24<01:35, 3.17s/it]\n 86%|████████▌ | 171/200 [05:24<01:05, 2.26s/it]\n 86%|████████▌ | 172/200 [05:27<01:13, 2.62s/it]\n 86%|████████▋ | 173/200 [05:27<00:51, 1.91s/it]\n 87%|████████▋ | 174/200 [05:31<01:03, 2.45s/it]\n 88%|████████▊ | 175/200 [05:31<00:43, 1.75s/it]\n 88%|████████▊ | 176/200 [05:31<00:31, 1.30s/it]\n 88%|████████▊ | 177/200 [05:35<00:45, 1.98s/it]\n 89%|████████▉ | 178/200 [05:35<00:32, 1.48s/it]\n 90%|████████▉ | 179/200 [05:39<00:43, 2.08s/it]\n 90%|█████████ | 180/200 [05:43<00:52, 2.62s/it]\n 90%|█████████ | 181/200 [05:46<00:54, 2.88s/it]\n 91%|█████████ | 182/200 [05:46<00:37, 2.06s/it]\n 92%|█████████▏| 183/200 [05:50<00:43, 2.58s/it]\n 92%|█████████▏| 184/200 [05:50<00:29, 1.85s/it]\n 92%|█████████▎| 185/200 [05:54<00:35, 2.36s/it]\n 93%|█████████▎| 186/200 [05:54<00:24, 1.74s/it]\n 94%|█████████▎| 187/200 [05:58<00:30, 2.31s/it]\n 94%|█████████▍| 188/200 [06:01<00:32, 2.69s/it]\n 94%|█████████▍| 189/200 [06:05<00:32, 2.96s/it]\n 95%|█████████▌| 190/200 [06:09<00:31, 3.16s/it]\n 96%|█████████▌| 191/200 [06:09<00:20, 2.25s/it]\n 96%|█████████▌| 192/200 [06:12<00:21, 2.64s/it]\n 96%|█████████▋| 193/200 [06:16<00:20, 2.92s/it]\n 97%|█████████▋| 194/200 [06:19<00:18, 3.09s/it]\n 98%|█████████▊| 195/200 [06:23<00:16, 3.22s/it]\n 98%|█████████▊| 196/200 [06:26<00:13, 3.34s/it]\n 98%|█████████▊| 197/200 [06:30<00:10, 3.38s/it]\n 99%|█████████▉| 198/200 [06:34<00:06, 3.45s/it]\n100%|█████████▉| 199/200 [06:34<00:02, 2.47s/it]\n100%|██████████| 200/200 [06:37<00:00, 2.84s/it]\n100%|██████████| 200/200 [06:37<00:00, 1.99s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752878667/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_1752878667/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_1752878667/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_1752878667/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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 (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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 397.939346075058\nerrors 95\nmean length: 1.575\n\nthroughput (request / second): 0.5025891557912865\nthroughput (character / second): 0.7915779203712763\naverage request duration (s) 1.9895369040966033\n50%ile request duration (s) 3.4190064668655396\n75%ile request duration (s) 3.575618028640747\n90%ile request duration (s) 3.648307371139526\n95%ile request duration (s) 3.693989527225494\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-nis-8b-v1-llama3-48598-v5-profiler is running
Tearing down inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler
Service chaiml-nis-8b-v1-llama3-48598-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.60s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-nis-8b-v1-llama3-48598-v5-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 4.44s
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-nis-8b-v1-llama3-48598-v5-profiler
Waiting for inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler to be ready
Inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler ready after 162.15298008918762s
Pipeline stage MKMLProfilerDeployer completed in 162.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5:/code/chaiverse_profiler_1752879341 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752879341 && 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_1752879341/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5:/code/chaiverse_profiler_1752879796 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752879796 && 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_1752879796/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5:/code/chaiverse_profiler_1752880263 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-nis-8b-v1-lla05ee2a19472a2a03778f92166fc360ed-deploj44g5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752880263 && 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_1752880263/summary.json'
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nUnable to use a TTY - input is not a terminal or the right kind of file\n\n 0%| | 0/200 [00:00<?, ?it/s]\n 0%| | 1/200 [00:00<00:26, 7.61it/s]\n 1%| | 2/200 [00:03<07:16, 2.21s/it]\n 2%|▏ | 3/200 [00:07<09:56, 3.03s/it]\n 2%|▏ | 4/200 [00:11<10:31, 3.22s/it]\n 2%|▎ | 5/200 [00:14<10:54, 3.36s/it]\n 3%|▎ | 6/200 [00:15<07:18, 2.26s/it]\n 4%|▎ | 7/200 [00:18<08:45, 2.73s/it]\n 4%|▍ | 8/200 [00:22<09:37, 3.01s/it]\n 4%|▍ | 9/200 [00:22<06:42, 2.11s/it]\n 5%|▌ | 10/200 [00:26<08:05, 2.55s/it]\n 6%|▌ | 11/200 [00:29<09:02, 2.87s/it]\n 6%|▌ | 12/200 [00:33<09:47, 3.13s/it]\n 6%|▋ | 13/200 [00:36<10:15, 3.29s/it]\n 7%|▋ | 14/200 [00:40<10:19, 3.33s/it]\n 8%|▊ | 15/200 [00:40<07:25, 2.41s/it]\n 8%|▊ | 16/200 [00:40<05:24, 1.76s/it]\n 8%|▊ | 17/200 [00:41<03:59, 1.31s/it]\n 9%|▉ | 18/200 [00:44<05:56, 1.96s/it]\n 10%|▉ | 19/200 [00:48<07:25, 2.46s/it]\n 10%|█ | 20/200 [00:48<05:24, 1.80s/it]\n 10%|█ | 21/200 [00:48<04:01, 1.35s/it]\n 11%|█ | 22/200 [00:49<03:02, 1.03s/it]\n 12%|█▏ | 23/200 [00:49<02:22, 1.24it/s]\n 12%|█▏ | 24/200 [00:53<04:51, 1.66s/it]\n 12%|█▎ | 25/200 [00:56<06:29, 2.23s/it]\n 13%|█▎ | 26/200 [00:56<04:44, 1.63s/it]\n 14%|█▎ | 27/200 [01:00<06:26, 2.23s/it]\n 14%|█▍ | 28/200 [01:00<04:43, 1.65s/it]\n 14%|█▍ | 29/200 [01:04<06:16, 2.20s/it]\n 15%|█▌ | 30/200 [01:07<07:31, 2.65s/it]\n 16%|█▌ | 31/200 [01:08<05:20, 1.90s/it]\n 16%|█▌ | 32/200 [01:08<03:57, 1.41s/it]\n 16%|█▋ | 33/200 [01:12<05:54, 2.12s/it]\n 17%|█▋ | 34/200 [01:15<07:01, 2.54s/it]\n 18%|█▊ | 35/200 [01:15<05:00, 1.82s/it]\n 18%|█▊ | 36/200 [01:16<03:43, 1.36s/it]\n 18%|█▊ | 37/200 [01:19<05:35, 2.06s/it]\n 19%|█▉ | 38/200 [01:20<04:07, 1.53s/it]\n 20%|█▉ | 39/200 [01:20<03:06, 1.16s/it]\n 20%|██ | 40/200 [01:20<02:23, 1.12it/s]\n 20%|██ | 41/200 [01:20<01:52, 1.42it/s]\n 21%|██ | 42/200 [01:24<04:07, 1.56s/it]\n 22%|██▏ | 43/200 [01:24<03:07, 1.19s/it]\n 22%|██▏ | 44/200 [01:25<02:24, 1.08it/s]\n 22%|██▎ | 45/200 [01:25<01:54, 1.36it/s]\n 23%|██▎ | 46/200 [01:25<01:32, 1.67it/s]\n 24%|██▎ | 47/200 [01:29<03:47, 1.49s/it]\n 24%|██▍ | 48/200 [01:32<05:24, 2.14s/it]\n 24%|██▍ | 49/200 [01:33<03:51, 1.53s/it]\n 25%|██▌ | 50/200 [01:36<05:21, 2.14s/it]\n 26%|██▌ | 51/200 [01:36<03:58, 1.60s/it]\n 26%|██▌ | 52/200 [01:40<05:25, 2.20s/it]\n 26%|██▋ | 53/200 [01:40<03:59, 1.63s/it]\n 27%|██▋ | 54/200 [01:44<05:27, 2.24s/it]\n 28%|██▊ | 55/200 [01:47<06:18, 2.61s/it]\n 28%|██▊ | 56/200 [01:51<06:59, 2.91s/it]\n 28%|██▊ | 57/200 [01:55<07:20, 3.08s/it]\n 29%|██▉ | 58/200 [01:58<07:40, 3.24s/it]\n 30%|██▉ | 59/200 [02:02<07:49, 3.33s/it]\n 30%|███ | 60/200 [02:05<07:48, 3.35s/it]\n 30%|███ | 61/200 [02:09<07:59, 3.45s/it]\n 31%|███ | 62/200 [02:12<08:01, 3.49s/it]\n 32%|███▏ | 63/200 [02:16<08:01, 3.51s/it]\n 32%|███▏ | 64/200 [02:19<07:55, 3.49s/it]\n 32%|███▎ | 65/200 [02:23<07:53, 3.51s/it]\n 33%|███▎ | 66/200 [02:26<07:49, 3.50s/it]\n 34%|███▎ | 67/200 [02:30<07:50, 3.54s/it]\n 34%|███▍ | 68/200 [02:34<07:46, 3.53s/it]\n 34%|███▍ | 69/200 [02:34<05:29, 2.51s/it]\n 35%|███▌ | 70/200 [02:37<06:16, 2.89s/it]\n 36%|███▌ | 71/200 [02:41<06:40, 3.11s/it]\n 36%|███▌ | 72/200 [02:45<06:55, 3.24s/it]\n 36%|███▋ | 73/200 [02:45<04:53, 2.31s/it]\n 37%|███▋ | 74/200 [02:49<05:46, 2.75s/it]\n 38%|███▊ | 75/200 [02:49<04:05, 1.96s/it]\n 38%|███▊ | 76/200 [02:52<04:59, 2.41s/it]\n 38%|███▊ | 77/200 [02:56<05:48, 2.83s/it]\n 39%|███▉ | 78/200 [02:56<04:06, 2.02s/it]\n 40%|███▉ | 79/200 [02:56<03:01, 1.50s/it]\n 40%|████ | 80/200 [03:00<04:12, 2.10s/it]\n 40%|████ | 81/200 [03:04<05:23, 2.72s/it]\n 41%|████ | 82/200 [03:08<05:59, 3.05s/it]\n 42%|████▏ | 83/200 [03:11<06:12, 3.18s/it]\n 42%|████▏ | 84/200 [03:15<06:33, 3.39s/it]\n 42%|████▎ | 85/200 [03:15<04:38, 2.42s/it]\n 43%|████▎ | 86/200 [03:19<05:22, 2.83s/it]\n 44%|████▎ | 87/200 [03:23<05:53, 3.13s/it]\n 44%|████▍ | 88/200 [03:27<06:07, 3.28s/it]\n 44%|████▍ | 89/200 [03:30<06:17, 3.40s/it]\n 45%|████▌ | 90/200 [03:30<04:26, 2.42s/it]\n 46%|████▌ | 91/200 [03:31<03:15, 1.79s/it]\n 46%|████▌ | 92/200 [03:34<04:13, 2.34s/it]\n 46%|████▋ | 93/200 [03:35<03:04, 1.72s/it]\n 47%|████▋ | 94/200 [03:35<02:17, 1.30s/it]\n 48%|████▊ | 95/200 [03:35<01:45, 1.00s/it]\n 48%|████▊ | 96/200 [03:39<03:07, 1.80s/it]\n 48%|████▊ | 97/200 [03:43<04:02, 2.36s/it]\n 49%|████▉ | 98/200 [03:43<02:56, 1.73s/it]\n 50%|████▉ | 99/200 [03:43<02:13, 1.32s/it]\n 50%|█████ | 100/200 [03:47<03:21, 2.01s/it]\n 50%|█████ | 101/200 [03:51<04:11, 2.54s/it]\n 51%|█████ | 102/200 [03:54<04:39, 2.85s/it]\n 52%|█████▏ | 103/200 [03:54<03:21, 2.07s/it]\n 52%|█████▏ | 104/200 [03:55<02:28, 1.55s/it]\n 52%|█████▎ | 105/200 [03:58<03:27, 2.18s/it]\n 53%|█████▎ | 106/200 [03:59<02:27, 1.57s/it]\n 54%|█████▎ | 107/200 [03:59<01:51, 1.20s/it]\n 54%|█████▍ | 108/200 [04:03<03:00, 1.97s/it]\n 55%|█████▍ | 109/200 [04:06<03:45, 2.48s/it]\n 55%|█████▌ | 110/200 [04:07<02:39, 1.78s/it]\n 56%|█████▌ | 111/200 [04:10<03:31, 2.38s/it]\n 56%|█████▌ | 112/200 [04:14<04:00, 2.74s/it]\n 56%|█████▋ | 113/200 [04:18<04:22, 3.01s/it]\n 57%|█████▋ | 114/200 [04:18<03:04, 2.15s/it]\n 57%|█████▊ | 115/200 [04:18<02:15, 1.59s/it]\n 58%|█████▊ | 116/200 [04:22<03:06, 2.22s/it]\n 58%|█████▊ | 117/200 [04:25<03:39, 2.64s/it]\n 59%|█████▉ | 118/200 [04:29<04:01, 2.94s/it]\n 60%|█████▉ | 119/200 [04:29<02:50, 2.10s/it]\n 60%|██████ | 120/200 [04:33<03:30, 2.63s/it]\n 60%|██████ | 121/200 [04:33<02:28, 1.88s/it]\n 61%|██████ | 122/200 [04:37<03:05, 2.38s/it]\n 62%|██████▏ | 123/200 [04:37<02:14, 1.75s/it]\n 62%|██████▏ | 124/200 [04:41<02:59, 2.36s/it]\n 62%|██████▎ | 125/200 [04:41<02:06, 1.69s/it]\n 63%|██████▎ | 126/200 [04:45<02:50, 2.30s/it]\n 64%|██████▎ | 127/200 [04:45<02:00, 1.66s/it]\n 64%|██████▍ | 128/200 [04:45<01:30, 1.25s/it]\n 64%|██████▍ | 129/200 [04:49<02:18, 1.95s/it]\n 65%|██████▌ | 130/200 [04:52<02:55, 2.51s/it]\n 66%|██████▌ | 131/200 [04:56<03:15, 2.84s/it]\n 66%|██████▌ | 132/200 [04:56<02:17, 2.03s/it]\n 66%|██████▋ | 133/200 [05:00<02:52, 2.58s/it]\n 67%|██████▋ | 134/200 [05:00<02:01, 1.85s/it]\n 68%|██████▊ | 135/200 [05:04<02:39, 2.45s/it]\n 68%|██████▊ | 136/200 [05:04<01:52, 1.76s/it]\n 68%|██████▊ | 137/200 [05:04<01:23, 1.33s/it]\n 69%|██████▉ | 138/200 [05:08<02:08, 2.07s/it]\n 70%|██████▉ | 139/200 [05:12<02:39, 2.62s/it]\n 70%|███████ | 140/200 [05:16<02:56, 2.94s/it]\n 70%|███████ | 141/200 [05:19<03:05, 3.14s/it]\n 71%|███████ | 142/200 [05:20<02:09, 2.24s/it]\n 72%|███████▏ | 143/200 [05:23<02:36, 2.74s/it]\n 72%|███████▏ | 144/200 [05:24<01:50, 1.97s/it]\n 72%|███████▎ | 145/200 [05:24<01:20, 1.46s/it]\n 73%|███████▎ | 146/200 [05:24<00:59, 1.11s/it]\n 74%|███████▎ | 147/200 [05:28<01:38, 1.85s/it]\n 74%|███████▍ | 148/200 [05:28<01:12, 1.39s/it]\n 74%|███████▍ | 149/200 [05:32<01:44, 2.06s/it]\n 75%|███████▌ | 150/200 [05:35<02:06, 2.54s/it]\n 76%|███████▌ | 151/200 [05:39<02:21, 2.89s/it]\n 76%|███████▌ | 152/200 [05:43<02:30, 3.14s/it]\n 76%|███████▋ | 153/200 [05:43<01:45, 2.24s/it]\n 77%|███████▋ | 154/200 [05:47<02:04, 2.70s/it]\n 78%|███████▊ | 155/200 [05:50<02:14, 2.98s/it]\n 78%|███████▊ | 156/200 [05:54<02:19, 3.17s/it]\n 78%|███████▊ | 157/200 [05:58<02:22, 3.32s/it]\n 79%|███████▉ | 158/200 [06:01<02:23, 3.43s/it]\n 80%|███████▉ | 159/200 [06:05<02:22, 3.47s/it]\n 80%|████████ | 160/200 [06:05<01:38, 2.47s/it]\n 80%|████████ | 161/200 [06:09<01:52, 2.88s/it]\n 81%|████████ | 162/200 [06:09<01:18, 2.06s/it]\n 82%|████████▏ | 163/200 [06:09<00:56, 1.54s/it]\n 82%|████████▏ | 164/200 [06:10<00:42, 1.18s/it]\n 82%|████████▎ | 165/200 [06:13<01:07, 1.92s/it]\n 83%|████████▎ | 166/200 [06:14<00:48, 1.42s/it]\n 84%|████████▎ | 167/200 [06:17<01:09, 2.10s/it]\n 84%|████████▍ | 168/200 [06:18<00:49, 1.54s/it]\n 84%|████████▍ | 169/200 [06:21<01:07, 2.18s/it]\n 85%|████████▌ | 170/200 [06:21<00:48, 1.62s/it]\n 86%|████████▌ | 171/200 [06:22<00:35, 1.23s/it]\n 86%|████████▌ | 172/200 [06:25<00:54, 1.94s/it]\n 86%|████████▋ | 173/200 [06:29<01:06, 2.47s/it]\n 87%|████████▋ | 174/200 [06:33<01:13, 2.83s/it]\n 88%|████████▊ | 175/200 [06:36<01:16, 3.06s/it]\n 88%|████████▊ | 176/200 [06:40<01:17, 3.23s/it]\n 88%|████████▊ | 177/200 [06:40<00:53, 2.31s/it]\n 89%|████████▉ | 178/200 [06:40<00:37, 1.71s/it]\n 90%|████████▉ | 179/200 [06:41<00:27, 1.29s/it]\n 90%|█████████ | 180/200 [06:44<00:39, 1.98s/it]\n 90%|█████████ | 181/200 [06:48<00:46, 2.47s/it]\n 91%|█████████ | 182/200 [06:52<00:50, 2.82s/it]\n 92%|█████████▏| 183/200 [06:55<00:52, 3.06s/it]\n 92%|█████████▏| 184/200 [06:56<00:35, 2.22s/it]\n 92%|█████████▎| 185/200 [06:59<00:39, 2.64s/it]\n 93%|█████████▎| 186/200 [07:03<00:41, 2.93s/it]\n 94%|█████████▎| 187/200 [07:06<00:40, 3.14s/it]\n 94%|█████████▍| 188/200 [07:10<00:40, 3.34s/it]\n 94%|█████████▍| 189/200 [07:10<00:26, 2.38s/it]\n 95%|█████████▌| 190/200 [07:14<00:28, 2.84s/it]\n 96%|█████████▌| 191/200 [07:14<00:18, 2.03s/it]\n 96%|█████████▌| 192/200 [07:15<00:12, 1.50s/it]\n 96%|█████████▋| 193/200 [07:18<00:15, 2.20s/it]\n 97%|█████████▋| 194/200 [07:22<00:15, 2.61s/it]\n 98%|█████████▊| 195/200 [07:26<00:14, 2.89s/it]\n 98%|█████████▊| 196/200 [07:26<00:08, 2.12s/it]\n 98%|█████████▊| 197/200 [07:30<00:07, 2.63s/it]\n 99%|█████████▉| 198/200 [07:33<00:05, 2.94s/it]\n100%|█████████▉| 199/200 [07:34<00:02, 2.11s/it]\n100%|██████████| 200/200 [07:34<00:00, 1.58s/it]\n100%|██████████| 200/200 [07:34<00:00, 2.27s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752880263/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_1752880263/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_1752880263/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_1752880263/profiles.py", line 277, in run_batch_profile\n analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n f.write(json.dumps(row) + \'\\n\')\n File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n return _default_encoder.encode(obj)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n chunks = self.iterencode(o, _one_shot=True)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n return _iterencode(o, 0)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : 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): 454.4146316051483\nerrors 81\nmean length: 1.785\n\nthroughput (request / second): 0.44012667306405034\nthroughput (character / second): 0.7856261114193299\naverage request duration (s) 2.2719272100925445\n50%ile request duration (s) 3.553630232810974\n75%ile request duration (s) 3.6554794311523438\n90%ile request duration (s) 3.7841682910919188\n95%ile request duration (s) 3.8311336159706113\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-nis-8b-v1-llama3-48598-v5-profiler is running
Tearing down inference service chaiml-nis-8b-v1-llama3-48598-v5-profiler
Service chaiml-nis-8b-v1-llama3-48598-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.94s
Shutdown handler de-registered
chaiml-nis-8b-v1-llama3_48598_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-8b-v1-llama3_48598_v5 status is now torndown due to DeploymentManager action
chaiml-nis-8b-v1-llama3_48598_v5 status is now torndown due to DeploymentManager action