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-20250611-retune-1558-v10-mkmlizer
Waiting for job on chaiml-20250611-retune-1558-v10-mkmlizer to finish
chaiml-20250611-retune-1558-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Version: 0.29.15 ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ https://mk1.ai ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ belonging to: ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Chai Research Corp. ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-20250611-retune-1558-v10-mkmlizer: ║ ║
chaiml-20250611-retune-1558-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250611-retune-1558-v10-mkmlizer: Downloaded to shared memory in 14.474s
chaiml-20250611-retune-1558-v10-mkmlizer: Checking if ChaiML/20250611_retune_US_7_to_13_seconds already exists in ChaiML
chaiml-20250611-retune-1558-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpz8b6_r_9, device:0
chaiml-20250611-retune-1558-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250611-retune-1558-v10-mkmlizer: quantized model in 19.322s
chaiml-20250611-retune-1558-v10-mkmlizer: Processed model ChaiML/20250611_retune_US_7_to_13_seconds in 33.796s
chaiml-20250611-retune-1558-v10-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250611-retune-1558-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250611-retune-1558-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v10/nvidia
chaiml-20250611-retune-1558-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v10/nvidia/config.json
chaiml-20250611-retune-1558-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v10/nvidia/special_tokens_map.json
chaiml-20250611-retune-1558-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v10/nvidia/tokenizer_config.json
chaiml-20250611-retune-1558-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-20250611-retune-1558-v10/nvidia/tokenizer.json
Job chaiml-20250611-retune-1558-v10-mkmlizer completed after 57.44s with status: succeeded
Stopping job with name chaiml-20250611-retune-1558-v10-mkmlizer
Pipeline stage MKMLizer completed in 58.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.63s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-20250611-retune-1558-v10
Waiting for inference service chaiml-20250611-retune-1558-v10 to be ready
Failed to get response for submission junhua024-chai-06-full-_75415_v8: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-06-full-_75415_v7: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-06-full-_75415_v7: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-06-full-_75415_v8: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-06-full-_75415_v7: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7099344e1c10>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Failed to get response for submission junhua024-chai-06-full-_75415_v7: HTTPConnectionPool(host='junhua024-chai-06-full-75415-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-20250611-retune-1558-v10 ready after 305.92877292633057s
Pipeline stage MKMLDeployer completed in 307.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.218249082565308s
Received healthy response to inference request in 3.6564927101135254s
Received healthy response to inference request in 2.7301113605499268s
Received healthy response to inference request in 2.401916265487671s
Received healthy response to inference request in 4.258434295654297s
5 requests
0 failed requests
5th percentile: 2.467555284500122
10th percentile: 2.5331943035125732
20th percentile: 2.6644723415374756
30th percentile: 2.9153876304626465
40th percentile: 3.285940170288086
50th percentile: 3.6564927101135254
60th percentile: 3.897269344329834
70th percentile: 4.138045978546143
80th percentile: 4.450397253036499
90th percentile: 4.834323167800903
95th percentile: 5.0262861251831055
99th percentile: 5.179856491088867
mean time: 3.6530407428741456
Pipeline stage StressChecker completed in 21.21s
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 1.16s
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 2.08s
Shutdown handler de-registered
chaiml-20250611-retune-_1558_v10 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 0.11s
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-20250611-retune-1558-v10-profiler
Waiting for inference service chaiml-20250611-retune-1558-v10-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...
%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-20250611-retune-1558-v10-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 4.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-20250611-retune-1558-v10-profiler
Waiting for inference service chaiml-20250611-retune-1558-v10-profiler to be ready
Inference service chaiml-20250611-retune-1558-v10-profiler ready after 212.1354274749756s
Pipeline stage MKMLProfilerDeployer completed in 212.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l:/code/chaiverse_profiler_1752793382 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752793382 && 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_1752793382/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l:/code/chaiverse_profiler_1752793826 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752793826 && 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_1752793826/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l:/code/chaiverse_profiler_1752794248 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-20250611-retu688959792a50b3c4e10d3fc63278294e-deplox2q5l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752794248 && 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_1752794248/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<11:08, 3.36s/it]\n 1%| | 2/200 [00:06<11:10, 3.39s/it]\n 2%|▏ | 3/200 [00:10<11:07, 3.39s/it]\n 2%|▏ | 4/200 [00:10<06:59, 2.14s/it]\n 2%|▎ | 5/200 [00:13<08:25, 2.59s/it]\n 3%|▎ | 6/200 [00:17<09:15, 2.87s/it]\n 4%|▎ | 7/200 [00:17<06:25, 2.00s/it]\n 4%|▍ | 8/200 [00:20<07:56, 2.48s/it]\n 4%|▍ | 9/200 [00:24<08:49, 2.77s/it]\n 5%|▌ | 10/200 [00:24<06:11, 1.95s/it]\n 6%|▌ | 11/200 [00:24<04:30, 1.43s/it]\n 6%|▌ | 12/200 [00:24<03:21, 1.07s/it]\n 6%|▋ | 13/200 [00:25<02:33, 1.22it/s]\n 7%|▋ | 14/200 [00:25<02:00, 1.54it/s]\n 8%|▊ | 15/200 [00:28<04:36, 1.50s/it]\n 8%|▊ | 16/200 [00:32<06:19, 2.06s/it]\n 8%|▊ | 17/200 [00:35<07:36, 2.49s/it]\n 9%|▉ | 18/200 [00:39<08:40, 2.86s/it]\n 10%|▉ | 19/200 [00:39<06:16, 2.08s/it]\n 10%|█ | 20/200 [00:40<04:37, 1.54s/it]\n 10%|█ | 21/200 [00:40<03:21, 1.12s/it]\n 11%|█ | 22/200 [00:43<05:29, 1.85s/it]\n 12%|█▏ | 23/200 [00:47<07:00, 2.38s/it]\n 12%|█▏ | 24/200 [00:47<04:59, 1.70s/it]\n 12%|█▎ | 25/200 [00:50<06:31, 2.24s/it]\n 13%|█▎ | 26/200 [00:51<04:44, 1.63s/it]\n 14%|█▎ | 27/200 [00:54<06:25, 2.23s/it]\n 14%|█▍ | 28/200 [00:58<07:23, 2.58s/it]\n 14%|█▍ | 29/200 [00:58<05:14, 1.84s/it]\n 15%|█▌ | 30/200 [01:01<06:35, 2.32s/it]\n 16%|█▌ | 31/200 [01:05<07:34, 2.69s/it]\n 16%|█▌ | 32/200 [01:08<08:08, 2.91s/it]\n 16%|█▋ | 33/200 [01:12<08:30, 3.06s/it]\n 17%|█▋ | 34/200 [01:15<08:45, 3.17s/it]\n 18%|█▊ | 35/200 [01:15<06:11, 2.25s/it]\n 18%|█▊ | 36/200 [01:15<04:31, 1.65s/it]\n 18%|█▊ | 37/200 [01:19<06:00, 2.21s/it]\n 19%|█▉ | 38/200 [01:19<04:21, 1.61s/it]\n 20%|█▉ | 39/200 [01:19<03:14, 1.21s/it]\n 20%|██ | 40/200 [01:23<05:00, 1.88s/it]\n 20%|██ | 41/200 [01:23<03:39, 1.38s/it]\n 21%|██ | 42/200 [01:26<05:15, 2.00s/it]\n 22%|██▏ | 43/200 [01:30<06:21, 2.43s/it]\n 22%|██▏ | 44/200 [01:33<07:06, 2.73s/it]\n 22%|██▎ | 45/200 [01:37<07:37, 2.95s/it]\n 23%|██▎ | 46/200 [01:40<07:57, 3.10s/it]\n 24%|██▎ | 47/200 [01:41<05:43, 2.25s/it]\n 24%|██▍ | 48/200 [01:44<06:42, 2.65s/it]\n 24%|██▍ | 49/200 [01:44<04:45, 1.89s/it]\n 25%|██▌ | 50/200 [01:45<03:30, 1.40s/it]\n 26%|██▌ | 51/200 [01:45<02:37, 1.06s/it]\n 26%|██▌ | 52/200 [01:45<02:01, 1.22it/s]\n 26%|██▋ | 53/200 [01:49<04:00, 1.64s/it]\n 27%|██▋ | 54/200 [01:52<05:16, 2.17s/it]\n 28%|██▊ | 55/200 [01:55<06:12, 2.57s/it]\n 28%|██▊ | 56/200 [01:56<04:29, 1.87s/it]\n 28%|██▊ | 57/200 [01:59<05:36, 2.36s/it]\n 29%|██▉ | 58/200 [01:59<04:04, 1.72s/it]\n 30%|██▉ | 59/200 [02:03<05:16, 2.24s/it]\n 30%|███ | 60/200 [02:06<06:06, 2.61s/it]\n 30%|███ | 61/200 [02:10<06:38, 2.87s/it]\n 31%|███ | 62/200 [02:10<04:46, 2.07s/it]\n 32%|███▏ | 63/200 [02:14<05:40, 2.49s/it]\n 32%|███▏ | 64/200 [02:14<04:06, 1.81s/it]\n 32%|███▎ | 65/200 [02:14<03:01, 1.34s/it]\n 33%|███▎ | 66/200 [02:14<02:16, 1.02s/it]\n 34%|███▎ | 67/200 [02:18<03:52, 1.75s/it]\n 34%|███▍ | 68/200 [02:21<04:57, 2.26s/it]\n 34%|███▍ | 69/200 [02:21<03:35, 1.65s/it]\n 35%|███▌ | 70/200 [02:25<04:45, 2.20s/it]\n 36%|███▌ | 71/200 [02:28<05:31, 2.57s/it]\n 36%|███▌ | 72/200 [02:32<06:02, 2.84s/it]\n 36%|███▋ | 73/200 [02:32<04:22, 2.06s/it]\n 37%|███▋ | 74/200 [02:32<03:11, 1.52s/it]\n 38%|███▊ | 75/200 [02:33<02:22, 1.14s/it]\n 38%|███▊ | 76/200 [02:36<03:49, 1.85s/it]\n 38%|███▊ | 77/200 [02:40<04:48, 2.35s/it]\n 39%|███▉ | 78/200 [02:43<05:23, 2.65s/it]\n 40%|███▉ | 79/200 [02:46<05:49, 2.88s/it]\n 40%|████ | 80/200 [02:50<06:06, 3.05s/it]\n 40%|████ | 81/200 [02:53<06:19, 3.19s/it]\n 41%|████ | 82/200 [02:53<04:28, 2.27s/it]\n 42%|████▏ | 83/200 [02:57<05:10, 2.65s/it]\n 42%|████▏ | 84/200 [03:00<05:36, 2.90s/it]\n 42%|████▎ | 85/200 [03:04<05:51, 3.06s/it]\n 43%|████▎ | 86/200 [03:07<06:01, 3.17s/it]\n 44%|████▎ | 87/200 [03:07<04:14, 2.25s/it]\n 44%|████▍ | 88/200 [03:11<04:51, 2.60s/it]\n 44%|████▍ | 89/200 [03:11<03:30, 1.89s/it]\n 45%|████▌ | 90/200 [03:15<04:22, 2.39s/it]\n 46%|████▌ | 91/200 [03:18<04:56, 2.72s/it]\n 46%|████▌ | 92/200 [03:18<03:30, 1.95s/it]\n 46%|████▋ | 93/200 [03:22<04:19, 2.43s/it]\n 47%|████▋ | 94/200 [03:25<04:47, 2.71s/it]\n 48%|████▊ | 95/200 [03:25<03:26, 1.97s/it]\n 48%|████▊ | 96/200 [03:29<04:10, 2.41s/it]\n 48%|████▊ | 97/200 [03:32<04:44, 2.77s/it]\n 49%|████▉ | 98/200 [03:36<05:03, 2.98s/it]\n 50%|████▉ | 99/200 [03:39<05:15, 3.12s/it]\n 50%|█████ | 100/200 [03:39<03:41, 2.22s/it]\n 50%|█████ | 101/200 [03:40<02:41, 1.63s/it]\n 51%|█████ | 102/200 [03:40<01:59, 1.22s/it]\n 52%|█████▏ | 103/200 [03:40<01:29, 1.08it/s]\n 52%|█████▏ | 104/200 [03:44<02:41, 1.69s/it]\n 52%|█████▎ | 105/200 [03:47<03:29, 2.21s/it]\n 53%|█████▎ | 106/200 [03:51<04:02, 2.58s/it]\n 54%|█████▎ | 107/200 [03:51<02:55, 1.89s/it]\n 54%|█████▍ | 108/200 [03:54<03:36, 2.36s/it]\n 55%|█████▍ | 109/200 [03:58<04:05, 2.70s/it]\n 55%|█████▌ | 110/200 [04:01<04:22, 2.92s/it]\n 56%|█████▌ | 111/200 [04:05<04:33, 3.08s/it]\n 56%|█████▌ | 112/200 [04:05<03:15, 2.22s/it]\n 56%|█████▋ | 113/200 [04:08<03:48, 2.63s/it]\n 57%|█████▋ | 114/200 [04:09<02:41, 1.88s/it]\n 57%|█████▊ | 115/200 [04:09<01:58, 1.39s/it]\n 58%|█████▊ | 116/200 [04:12<02:52, 2.06s/it]\n 58%|█████▊ | 117/200 [04:16<03:26, 2.49s/it]\n 59%|█████▉ | 118/200 [04:16<02:25, 1.78s/it]\n 60%|█████▉ | 119/200 [04:16<01:46, 1.32s/it]\n 60%|██████ | 120/200 [04:20<02:38, 1.98s/it]\n 60%|██████ | 121/200 [04:23<03:09, 2.40s/it]\n 61%|██████ | 122/200 [04:27<03:30, 2.70s/it]\n 62%|██████▏ | 123/200 [04:30<03:47, 2.96s/it]\n 62%|██████▏ | 124/200 [04:30<02:40, 2.11s/it]\n 62%|██████▎ | 125/200 [04:34<03:07, 2.50s/it]\n 63%|██████▎ | 126/200 [04:34<02:14, 1.82s/it]\n 64%|██████▎ | 127/200 [04:37<02:50, 2.33s/it]\n 64%|██████▍ | 128/200 [04:41<03:11, 2.66s/it]\n 64%|██████▍ | 129/200 [04:44<03:24, 2.88s/it]\n 65%|██████▌ | 130/200 [04:48<03:33, 3.05s/it]\n 66%|██████▌ | 131/200 [04:51<03:37, 3.15s/it]\n 66%|██████▌ | 132/200 [04:55<03:40, 3.24s/it]\n 66%|██████▋ | 133/200 [04:58<03:40, 3.30s/it]\n 67%|██████▋ | 134/200 [04:58<02:34, 2.35s/it]\n 68%|██████▊ | 135/200 [05:02<02:56, 2.71s/it]\n 68%|██████▊ | 136/200 [05:05<03:07, 2.93s/it]\n 68%|██████▊ | 137/200 [05:05<02:11, 2.08s/it]\n 69%|██████▉ | 138/200 [05:09<02:34, 2.50s/it]\n 70%|██████▉ | 139/200 [05:12<02:49, 2.77s/it]\n 70%|███████ | 140/200 [05:12<02:00, 2.01s/it]\n 70%|███████ | 141/200 [05:16<02:24, 2.44s/it]\n 71%|███████ | 142/200 [05:16<01:43, 1.78s/it]\n 72%|███████▏ | 143/200 [05:20<02:11, 2.31s/it]\n 72%|███████▏ | 144/200 [05:20<01:32, 1.65s/it]\n 72%|███████▎ | 145/200 [05:23<02:01, 2.21s/it]\n 73%|███████▎ | 146/200 [05:27<02:19, 2.58s/it]\n 74%|███████▎ | 147/200 [05:30<02:29, 2.83s/it]\n 74%|███████▍ | 148/200 [05:30<01:44, 2.01s/it]\n 74%|███████▍ | 149/200 [05:30<01:15, 1.48s/it]\n 75%|███████▌ | 150/200 [05:34<01:43, 2.07s/it]\n 76%|███████▌ | 151/200 [05:34<01:14, 1.51s/it]\n 76%|███████▌ | 152/200 [05:34<00:54, 1.14s/it]\n 76%|███████▋ | 153/200 [05:35<00:40, 1.15it/s]\n 77%|███████▋ | 154/200 [05:35<00:31, 1.46it/s]\n 78%|███████▊ | 155/200 [05:38<01:08, 1.52s/it]\n 78%|███████▊ | 156/200 [05:42<01:31, 2.09s/it]\n 78%|███████▊ | 157/200 [05:42<01:05, 1.53s/it]\n 79%|███████▉ | 158/200 [05:42<00:48, 1.15s/it]\n 80%|███████▉ | 159/200 [05:42<00:34, 1.19it/s]\n 80%|████████ | 160/200 [05:46<01:05, 1.65s/it]\n 80%|████████ | 161/200 [05:49<01:24, 2.18s/it]\n 81%|████████ | 162/200 [05:49<00:59, 1.56s/it]\n 82%|████████▏ | 163/200 [05:50<00:43, 1.17s/it]\n 82%|████████▏ | 164/200 [05:50<00:32, 1.12it/s]\n 82%|████████▎ | 165/200 [05:50<00:24, 1.44it/s]\n 83%|████████▎ | 166/200 [05:54<00:51, 1.50s/it]\n 84%|████████▎ | 167/200 [05:57<01:08, 2.08s/it]\n 84%|████████▍ | 168/200 [06:00<01:19, 2.48s/it]\n 84%|████████▍ | 169/200 [06:04<01:26, 2.78s/it]\n 85%|████████▌ | 170/200 [06:04<01:00, 2.01s/it]\n 86%|████████▌ | 171/200 [06:04<00:42, 1.48s/it]\n 86%|████████▌ | 172/200 [06:08<00:57, 2.07s/it]\n 86%|████████▋ | 173/200 [06:08<00:40, 1.52s/it]\n 87%|████████▋ | 174/200 [06:08<00:29, 1.13s/it]\n 88%|████████▊ | 175/200 [06:08<00:21, 1.15it/s]\n 88%|████████▊ | 176/200 [06:12<00:39, 1.66s/it]\n 88%|████████▊ | 177/200 [06:15<00:49, 2.16s/it]\n 89%|████████▉ | 178/200 [06:19<00:55, 2.54s/it]\n 90%|████████▉ | 179/200 [06:19<00:38, 1.85s/it]\n 90%|█████████ | 180/200 [06:22<00:46, 2.31s/it]\n 90%|█████████ | 181/200 [06:26<00:50, 2.65s/it]\n 91%|█████████ | 182/200 [06:29<00:51, 2.88s/it]\n 92%|█████████▏| 183/200 [06:33<00:52, 3.08s/it]\n 92%|█████████▏| 184/200 [06:33<00:35, 2.19s/it]\n 92%|█████████▎| 185/200 [06:36<00:39, 2.60s/it]\n 93%|█████████▎| 186/200 [06:40<00:39, 2.85s/it]\n 94%|█████████▎| 187/200 [06:40<00:26, 2.04s/it]\n 94%|█████████▍| 188/200 [06:43<00:29, 2.48s/it]\n 94%|█████████▍| 189/200 [06:47<00:30, 2.76s/it]\n 95%|█████████▌| 190/200 [06:47<00:19, 1.97s/it]\n 96%|█████████▌| 191/200 [06:47<00:13, 1.45s/it]\n 96%|█████████▌| 192/200 [06:51<00:16, 2.05s/it]\n 96%|█████████▋| 193/200 [06:54<00:17, 2.48s/it]\n 97%|█████████▋| 194/200 [06:54<00:10, 1.80s/it]\n 98%|█████████▊| 195/200 [06:58<00:11, 2.28s/it]\n 98%|█████████▊| 196/200 [07:01<00:10, 2.62s/it]\n 98%|█████████▊| 197/200 [07:01<00:05, 1.90s/it]\n 99%|█████████▉| 198/200 [07:02<00:02, 1.40s/it]\n100%|█████████▉| 199/200 [07:02<00:01, 1.06s/it]\n100%|██████████| 200/200 [07:02<00:00, 1.23it/s]\n100%|██████████| 200/200 [07:02<00:00, 2.11s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752794248/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_1752794248/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_1752794248/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_1752794248/profiles.py", line 277, in run_batch_profile\n analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n f.write(json.dumps(row) + \'\\n\')\n File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n return _default_encoder.encode(obj)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n chunks = self.iterencode(o, _one_shot=True)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n return _iterencode(o, 0)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 422.713595867157\nerrors 83\nmean length: 1.755\n\nthroughput (request / second): 0.4731335872689851\nthroughput (character / second): 0.8303494456570688\naverage request duration (s) 2.113468347787857\n50%ile request duration (s) 3.4013147354125977\n75%ile request duration (s) 3.4588693976402283\n90%ile request duration (s) 3.5310551166534423\n95%ile request duration (s) 3.5511703491210938\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-20250611-retune-1558-v10-profiler is running
Tearing down inference service chaiml-20250611-retune-1558-v10-profiler
Service chaiml-20250611-retune-1558-v10-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.71s
Shutdown handler de-registered
chaiml-20250611-retune-_1558_v10 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250611-retune-_1558_v10 status is now torndown due to DeploymentManager action
chaiml-20250611-retune-_1558_v10 status is now torndown due to DeploymentManager action