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-llama31-mer-v2-t-44570-v2-mkmlizer
Waiting for job on chaiml-llama31-mer-v2-t-44570-v2-mkmlizer to finish
Failed to get response for submission chaiml-simon-ghost-rile_65921_v1: HTTPConnectionPool(host='chaiml-simon-ghost-rile-65921-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ belonging to: ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ║ ║
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: Downloaded to shared memory in 33.944s
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: Checking if ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 already exists in ChaiML
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp79x7p2ld, device:0
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-daren-god-of-deat_6797_v1: HTTPConnectionPool(host='chaiml-daren-god-of-deat-6797-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: quantized model in 25.134s
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: Processed model ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572 in 59.079s
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia/special_tokens_map.json
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia/config.json
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia/tokenizer_config.json
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia/tokenizer.json
chaiml-llama31-mer-v2-t-44570-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama31-mer-v2-t-44570-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-llama31-mer-v2-t-44570-v2-mkmlizer completed after 157.67s with status: succeeded
Stopping job with name chaiml-llama31-mer-v2-t-44570-v2-mkmlizer
Pipeline stage MKMLizer completed in 158.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama31-mer-v2-t-44570-v2
Waiting for inference service chaiml-llama31-mer-v2-t-44570-v2 to be ready
Failed to get response for submission chaiml-isaac-brown-sylu_53639_v2: HTTPConnectionPool(host='chaiml-isaac-brown-sylu-53639-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama31-mer-v2-t-44570-v2 ready after 321.0610365867615s
Pipeline stage MKMLDeployer completed in 321.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.814276933670044s
Received healthy response to inference request in 3.552907705307007s
Received healthy response to inference request in 2.8282716274261475s
Received healthy response to inference request in 3.2005457878112793s
Received healthy response to inference request in 4.663153409957886s
5 requests
0 failed requests
5th percentile: 2.9027264595031737
10th percentile: 2.9771812915802003
20th percentile: 3.126090955734253
30th percentile: 3.2710181713104247
40th percentile: 3.411962938308716
50th percentile: 3.552907705307007
60th percentile: 3.997005987167358
70th percentile: 4.44110426902771
80th percentile: 4.693378114700318
90th percentile: 4.753827524185181
95th percentile: 4.784052228927612
99th percentile: 4.8082319927215575
mean time: 3.8118310928344727
Pipeline stage StressChecker completed in 20.66s
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 0.86s
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 1.06s
Shutdown handler de-registered
chaiml-llama31-mer-v2-t_44570_v2 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...
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama31-mer-v2-t-44570-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 5.13s
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-llama31-mer-v2-t-44570-v2-profiler
Waiting for inference service chaiml-llama31-mer-v2-t-44570-v2-profiler to be ready
Inference service chaiml-llama31-mer-v2-t-44570-v2-profiler ready after 212.65194821357727s
Pipeline stage MKMLProfilerDeployer completed in 213.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7:/code/chaiverse_profiler_1752856630 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752856630 && 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_1752856630/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7:/code/chaiverse_profiler_1752857104 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752857104 && 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_1752857104/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7:/code/chaiverse_profiler_1752857549 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deplog5ll7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752857549 && 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_1752857549/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<00:27, 7.28it/s]\n 1%| | 2/200 [00:00<00:50, 3.94it/s]\n 2%|▏ | 3/200 [00:00<01:00, 3.24it/s]\n 2%|▏ | 4/200 [00:04<05:17, 1.62s/it]\n 2%|▎ | 5/200 [00:08<07:49, 2.41s/it]\n 3%|▎ | 6/200 [00:11<09:10, 2.84s/it]\n 4%|▎ | 7/200 [00:12<06:16, 1.95s/it]\n 4%|▍ | 8/200 [00:12<04:37, 1.44s/it]\n 4%|▍ | 9/200 [00:12<03:27, 1.09s/it]\n 5%|▌ | 10/200 [00:13<02:41, 1.18it/s]\n 6%|▌ | 11/200 [00:13<02:10, 1.45it/s]\n 6%|▌ | 12/200 [00:17<05:00, 1.60s/it]\n 6%|▋ | 13/200 [00:17<03:46, 1.21s/it]\n 7%|▋ | 14/200 [00:17<02:58, 1.04it/s]\n 8%|▊ | 15/200 [00:18<02:23, 1.29it/s]\n 8%|▊ | 16/200 [00:21<05:07, 1.67s/it]\n 8%|▊ | 17/200 [00:25<07:00, 2.30s/it]\n 9%|▉ | 18/200 [00:29<08:16, 2.73s/it]\n 10%|▉ | 19/200 [00:32<09:03, 3.00s/it]\n 10%|█ | 20/200 [00:36<09:38, 3.22s/it]\n 10%|█ | 21/200 [00:40<10:00, 3.36s/it]\n 11%|█ | 22/200 [00:44<10:12, 3.44s/it]\n 12%|█▏ | 23/200 [00:44<07:13, 2.45s/it]\n 12%|█▏ | 24/200 [00:48<08:24, 2.87s/it]\n 12%|█▎ | 25/200 [00:48<05:58, 2.05s/it]\n 13%|█▎ | 26/200 [00:48<04:27, 1.53s/it]\n 14%|█▎ | 27/200 [00:52<06:22, 2.21s/it]\n 14%|█▍ | 28/200 [00:56<07:40, 2.68s/it]\n 14%|█▍ | 29/200 [00:56<05:27, 1.92s/it]\n 15%|█▌ | 30/200 [00:56<04:05, 1.44s/it]\n 16%|█▌ | 31/200 [00:56<03:08, 1.12s/it]\n 16%|█▌ | 32/200 [00:57<02:29, 1.13it/s]\n 16%|█▋ | 33/200 [00:57<02:01, 1.37it/s]\n 17%|█▋ | 34/200 [01:01<04:26, 1.60s/it]\n 18%|█▊ | 35/200 [01:01<03:20, 1.22s/it]\n 18%|█▊ | 36/200 [01:05<05:20, 1.95s/it]\n 18%|█▊ | 37/200 [01:08<06:41, 2.47s/it]\n 19%|█▉ | 38/200 [01:12<07:37, 2.82s/it]\n 20%|█▉ | 39/200 [01:16<08:18, 3.10s/it]\n 20%|██ | 40/200 [01:16<06:01, 2.26s/it]\n 20%|██ | 41/200 [01:20<07:06, 2.69s/it]\n 21%|██ | 42/200 [01:20<05:11, 1.97s/it]\n 22%|██▏ | 43/200 [01:24<06:32, 2.50s/it]\n 22%|██▏ | 44/200 [01:27<07:25, 2.86s/it]\n 22%|██▎ | 45/200 [01:28<05:26, 2.11s/it]\n 23%|██▎ | 46/200 [01:28<03:54, 1.52s/it]\n 24%|██▎ | 47/200 [01:32<05:39, 2.22s/it]\n 24%|██▍ | 48/200 [01:32<04:02, 1.60s/it]\n 24%|██▍ | 49/200 [01:36<05:42, 2.27s/it]\n 25%|██▌ | 50/200 [01:40<06:53, 2.76s/it]\n 26%|██▌ | 51/200 [01:43<07:30, 3.02s/it]\n 26%|██▌ | 52/200 [01:43<05:19, 2.16s/it]\n 26%|██▋ | 53/200 [01:44<03:58, 1.62s/it]\n 27%|██▋ | 54/200 [01:48<05:25, 2.23s/it]\n 28%|██▊ | 55/200 [01:51<06:34, 2.72s/it]\n 28%|██▊ | 56/200 [01:55<07:11, 3.00s/it]\n 28%|██▊ | 57/200 [01:59<07:38, 3.21s/it]\n 29%|██▉ | 58/200 [02:02<07:55, 3.35s/it]\n 30%|██▉ | 59/200 [02:06<08:03, 3.43s/it]\n 30%|███ | 60/200 [02:10<08:08, 3.49s/it]\n 30%|███ | 61/200 [02:13<08:12, 3.54s/it]\n 31%|███ | 62/200 [02:17<08:12, 3.57s/it]\n 32%|███▏ | 63/200 [02:17<05:47, 2.54s/it]\n 32%|███▏ | 64/200 [02:21<06:37, 2.93s/it]\n 32%|███▎ | 65/200 [02:21<04:41, 2.09s/it]\n 33%|███▎ | 66/200 [02:21<03:28, 1.56s/it]\n 34%|███▎ | 67/200 [02:22<02:38, 1.19s/it]\n 34%|███▍ | 68/200 [02:25<04:15, 1.94s/it]\n 34%|███▍ | 69/200 [02:29<05:20, 2.44s/it]\n 35%|███▌ | 70/200 [02:33<06:05, 2.82s/it]\n 36%|███▌ | 71/200 [02:33<04:25, 2.06s/it]\n 36%|███▌ | 72/200 [02:37<05:32, 2.59s/it]\n 36%|███▋ | 73/200 [02:41<06:11, 2.93s/it]\n 37%|███▋ | 74/200 [02:44<06:39, 3.17s/it]\n 38%|███▊ | 75/200 [02:44<04:42, 2.26s/it]\n 38%|███▊ | 76/200 [02:48<05:42, 2.76s/it]\n 38%|███▊ | 77/200 [02:52<06:17, 3.07s/it]\n 39%|███▉ | 78/200 [02:52<04:27, 2.20s/it]\n 40%|███▉ | 79/200 [02:56<05:17, 2.62s/it]\n 40%|████ | 80/200 [02:56<03:51, 1.93s/it]\n 40%|████ | 81/200 [02:57<02:52, 1.45s/it]\n 41%|████ | 82/200 [03:00<04:10, 2.12s/it]\n 42%|████▏ | 83/200 [03:04<05:02, 2.58s/it]\n 42%|████▏ | 84/200 [03:04<03:39, 1.90s/it]\n 42%|████▎ | 85/200 [03:05<02:45, 1.44s/it]\n 43%|████▎ | 86/200 [03:08<03:59, 2.10s/it]\n 44%|████▎ | 87/200 [03:12<04:49, 2.56s/it]\n 44%|████▍ | 88/200 [03:15<05:24, 2.90s/it]\n 44%|████▍ | 89/200 [03:19<05:47, 3.13s/it]\n 45%|████▌ | 90/200 [03:23<06:10, 3.37s/it]\n 46%|████▌ | 91/200 [03:23<04:22, 2.41s/it]\n 46%|████▌ | 92/200 [03:24<03:13, 1.79s/it]\n 46%|████▋ | 93/200 [03:24<02:24, 1.35s/it]\n 47%|████▋ | 94/200 [03:28<03:37, 2.05s/it]\n 48%|████▊ | 95/200 [03:31<04:27, 2.55s/it]\n 48%|████▊ | 96/200 [03:32<03:14, 1.87s/it]\n 48%|████▊ | 97/200 [03:32<02:25, 1.41s/it]\n 49%|████▉ | 98/200 [03:36<03:36, 2.12s/it]\n 50%|████▉ | 99/200 [03:39<04:21, 2.59s/it]\n 50%|█████ | 100/200 [03:43<04:50, 2.90s/it]\n 50%|█████ | 101/200 [03:47<05:10, 3.13s/it]\n 51%|█████ | 102/200 [03:47<03:45, 2.30s/it]\n 52%|█████▏ | 103/200 [03:47<02:46, 1.72s/it]\n 52%|█████▏ | 104/200 [03:51<03:40, 2.29s/it]\n 52%|█████▎ | 105/200 [03:51<02:41, 1.70s/it]\n 53%|█████▎ | 106/200 [03:55<03:35, 2.29s/it]\n 54%|█████▎ | 107/200 [03:59<04:10, 2.70s/it]\n 54%|█████▍ | 108/200 [04:02<04:34, 2.99s/it]\n 55%|█████▍ | 109/200 [04:06<04:48, 3.18s/it]\n 55%|█████▌ | 110/200 [04:06<03:28, 2.32s/it]\n 56%|█████▌ | 111/200 [04:07<02:34, 1.74s/it]\n 56%|█████▌ | 112/200 [04:07<01:56, 1.32s/it]\n 56%|█████▋ | 113/200 [04:11<02:56, 2.03s/it]\n 57%|█████▋ | 114/200 [04:14<03:38, 2.55s/it]\n 57%|█████▊ | 115/200 [04:15<02:35, 1.83s/it]\n 58%|█████▊ | 116/200 [04:18<03:23, 2.42s/it]\n 58%|█████▊ | 117/200 [04:19<02:23, 1.73s/it]\n 59%|█████▉ | 118/200 [04:19<01:48, 1.32s/it]\n 60%|█████▉ | 119/200 [04:23<02:43, 2.02s/it]\n 60%|██████ | 120/200 [04:23<02:00, 1.50s/it]\n 60%|██████ | 121/200 [04:23<01:31, 1.15s/it]\n 61%|██████ | 122/200 [04:24<01:11, 1.09it/s]\n 62%|██████▏ | 123/200 [04:27<02:15, 1.76s/it]\n 62%|██████▏ | 124/200 [04:31<02:55, 2.31s/it]\n 62%|██████▎ | 125/200 [04:35<03:27, 2.77s/it]\n 63%|██████▎ | 126/200 [04:35<02:26, 1.97s/it]\n 64%|██████▎ | 127/200 [04:35<01:48, 1.48s/it]\n 64%|██████▍ | 128/200 [04:39<02:33, 2.14s/it]\n 64%|██████▍ | 129/200 [04:42<03:03, 2.59s/it]\n 65%|██████▌ | 130/200 [04:46<03:26, 2.94s/it]\n 66%|██████▌ | 131/200 [04:50<03:39, 3.18s/it]\n 66%|██████▌ | 132/200 [04:50<02:34, 2.26s/it]\n 66%|██████▋ | 133/200 [04:54<02:59, 2.68s/it]\n 67%|██████▋ | 134/200 [04:58<03:18, 3.01s/it]\n 68%|██████▊ | 135/200 [04:58<02:19, 2.15s/it]\n 68%|██████▊ | 136/200 [05:01<02:47, 2.61s/it]\n 68%|██████▊ | 137/200 [05:05<03:08, 2.99s/it]\n 69%|██████▉ | 138/200 [05:09<03:17, 3.19s/it]\n 70%|██████▉ | 139/200 [05:13<03:23, 3.33s/it]\n 70%|███████ | 140/200 [05:16<03:25, 3.43s/it]\n 70%|███████ | 141/200 [05:16<02:23, 2.44s/it]\n 71%|███████ | 142/200 [05:17<01:44, 1.81s/it]\n 72%|███████▏ | 143/200 [05:20<02:14, 2.37s/it]\n 72%|███████▏ | 144/200 [05:24<02:34, 2.75s/it]\n 72%|███████▎ | 145/200 [05:28<02:46, 3.02s/it]\n 73%|███████▎ | 146/200 [05:28<01:59, 2.20s/it]\n 74%|███████▎ | 147/200 [05:28<01:27, 1.64s/it]\n 74%|███████▍ | 148/200 [05:32<01:57, 2.26s/it]\n 74%|███████▍ | 149/200 [05:32<01:25, 1.67s/it]\n 75%|███████▌ | 150/200 [05:33<01:03, 1.27s/it]\n 76%|███████▌ | 151/200 [05:33<00:48, 1.02it/s]\n 76%|███████▌ | 152/200 [05:33<00:37, 1.27it/s]\n 76%|███████▋ | 153/200 [05:37<01:18, 1.66s/it]\n 77%|███████▋ | 154/200 [05:41<01:45, 2.29s/it]\n 78%|███████▊ | 155/200 [05:44<02:01, 2.69s/it]\n 78%|███████▊ | 156/200 [05:48<02:10, 2.97s/it]\n 78%|███████▊ | 157/200 [05:52<02:17, 3.20s/it]\n 79%|███████▉ | 158/200 [05:55<02:20, 3.35s/it]\n 80%|███████▉ | 159/200 [05:59<02:22, 3.47s/it]\n 80%|████████ | 160/200 [06:03<02:21, 3.54s/it]\n 80%|████████ | 161/200 [06:07<02:19, 3.59s/it]\n 81%|████████ | 162/200 [06:07<01:36, 2.55s/it]\n 82%|████████▏ | 163/200 [06:07<01:10, 1.89s/it]\n 82%|████████▏ | 164/200 [06:07<00:51, 1.43s/it]\n 82%|████████▎ | 165/200 [06:11<01:14, 2.12s/it]\n 83%|████████▎ | 166/200 [06:15<01:27, 2.58s/it]\n 84%|████████▎ | 167/200 [06:18<01:35, 2.90s/it]\n 84%|████████▍ | 168/200 [06:19<01:08, 2.13s/it]\n 84%|████████▍ | 169/200 [06:19<00:49, 1.60s/it]\n 85%|████████▌ | 170/200 [06:23<01:07, 2.23s/it]\n 86%|████████▌ | 171/200 [06:27<01:17, 2.69s/it]\n 86%|████████▌ | 172/200 [06:27<00:55, 1.99s/it]\n 86%|████████▋ | 173/200 [06:27<00:40, 1.50s/it]\n 87%|████████▋ | 174/200 [06:31<00:57, 2.20s/it]\n 88%|████████▊ | 175/200 [06:35<01:06, 2.67s/it]\n 88%|████████▊ | 176/200 [06:35<00:45, 1.91s/it]\n 88%|████████▊ | 177/200 [06:39<00:57, 2.51s/it]\n 89%|████████▉ | 178/200 [06:43<01:03, 2.87s/it]\n 90%|████████▉ | 179/200 [06:43<00:43, 2.05s/it]\n 90%|█████████ | 180/200 [06:43<00:30, 1.54s/it]\n 90%|█████████ | 181/200 [06:43<00:22, 1.18s/it]\n 91%|█████████ | 182/200 [06:47<00:34, 1.92s/it]\n 92%|█████████▏| 183/200 [06:47<00:24, 1.44s/it]\n 92%|█████████▏| 184/200 [06:51<00:33, 2.10s/it]\n 92%|█████████▎| 185/200 [06:51<00:23, 1.56s/it]\n 93%|█████████▎| 186/200 [06:52<00:16, 1.20s/it]\n 94%|█████████▎| 187/200 [06:55<00:25, 1.96s/it]\n 94%|█████████▍| 188/200 [06:56<00:17, 1.46s/it]\n 94%|█████████▍| 189/200 [06:56<00:12, 1.13s/it]\n 95%|█████████▌| 190/200 [07:00<00:19, 1.95s/it]\n 96%|█████████▌| 191/200 [07:04<00:21, 2.43s/it]\n 96%|█████████▌| 192/200 [07:07<00:22, 2.79s/it]\n 96%|█████████▋| 193/200 [07:11<00:21, 3.14s/it]\n 97%|█████████▋| 194/200 [07:15<00:19, 3.28s/it]\n 98%|█████████▊| 195/200 [07:18<00:17, 3.41s/it]\n 98%|█████████▊| 196/200 [07:22<00:13, 3.49s/it]\n 98%|█████████▊| 197/200 [07:26<00:10, 3.55s/it]\n 99%|█████████▉| 198/200 [07:30<00:07, 3.61s/it]\n100%|█████████▉| 199/200 [07:33<00:03, 3.63s/it]\n100%|██████████| 200/200 [07:33<00:00, 2.58s/it]\n100%|██████████| 200/200 [07:33<00:00, 2.27s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752857549/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_1752857549/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_1752857549/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_1752857549/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 (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 (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): 453.8865842819214\nerrors 84\nmean length: 1.74\n\nthroughput (request / second): 0.44063871223780104\nthroughput (character / second): 0.7667113592937739\naverage request duration (s) 2.2692586433887483\n50%ile request duration (s) 3.638177514076233\n75%ile request duration (s) 3.694774031639099\n90%ile request duration (s) 3.7827036142349244\n95%ile request duration (s) 3.8462696075439453\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-llama31-mer-v2-t-44570-v2-profiler is running
Tearing down inference service chaiml-llama31-mer-v2-t-44570-v2-profiler
Service chaiml-llama31-mer-v2-t-44570-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.16s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama31-mer-v2-t-44570-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 5.73s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama31-mer-v2-t-44570-v2-profiler
Waiting for inference service chaiml-llama31-mer-v2-t-44570-v2-profiler to be ready
Inference service chaiml-llama31-mer-v2-t-44570-v2-profiler ready after 314.03892946243286s
Pipeline stage MKMLProfilerDeployer completed in 314.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b:/code/chaiverse_profiler_1752858432 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752858432 && 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_1752858432/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b:/code/chaiverse_profiler_1752858865 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752858865 && 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_1752858865/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b:/code/chaiverse_profiler_1752859283 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama31-mer-v378ec14110f2ebd18bdc4dbd4bfbdcc0-deploxpt9b --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1752859283 && 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_1752859283/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<00:57, 3.44it/s]\n 1%| | 2/200 [00:00<00:58, 3.37it/s]\n 2%|▏ | 3/200 [00:00<00:59, 3.29it/s]\n 2%|▏ | 4/200 [00:01<01:01, 3.17it/s]\n 2%|▎ | 5/200 [00:04<04:35, 1.42s/it]\n 3%|▎ | 6/200 [00:07<06:44, 2.08s/it]\n 4%|▎ | 7/200 [00:08<04:38, 1.45s/it]\n 4%|▍ | 8/200 [00:11<06:47, 2.12s/it]\n 4%|▍ | 9/200 [00:11<04:46, 1.50s/it]\n 5%|▌ | 10/200 [00:15<06:40, 2.11s/it]\n 6%|▌ | 11/200 [00:15<04:54, 1.56s/it]\n 6%|▌ | 12/200 [00:19<06:41, 2.13s/it]\n 6%|▋ | 13/200 [00:22<08:03, 2.58s/it]\n 7%|▋ | 14/200 [00:25<08:36, 2.77s/it]\n 8%|▊ | 15/200 [00:29<09:18, 3.02s/it]\n 8%|▊ | 16/200 [00:32<09:37, 3.14s/it]\n 8%|▊ | 17/200 [00:36<09:39, 3.17s/it]\n 9%|▉ | 18/200 [00:36<06:59, 2.31s/it]\n 10%|▉ | 19/200 [00:36<05:08, 1.70s/it]\n 10%|█ | 20/200 [00:40<06:37, 2.21s/it]\n 10%|█ | 21/200 [00:40<04:53, 1.64s/it]\n 11%|█ | 22/200 [00:40<03:39, 1.23s/it]\n 12%|█▏ | 23/200 [00:44<05:30, 1.87s/it]\n 12%|█▏ | 24/200 [00:47<06:55, 2.36s/it]\n 12%|█▎ | 25/200 [00:47<04:57, 1.70s/it]\n 13%|█▎ | 26/200 [00:48<03:42, 1.28s/it]\n 14%|█▎ | 27/200 [00:51<05:34, 1.93s/it]\n 14%|█▍ | 28/200 [00:54<06:49, 2.38s/it]\n 14%|█▍ | 29/200 [00:55<04:51, 1.70s/it]\n 15%|█▌ | 30/200 [00:55<03:38, 1.29s/it]\n 16%|█▌ | 31/200 [00:58<05:27, 1.94s/it]\n 16%|█▌ | 32/200 [00:59<04:01, 1.44s/it]\n 16%|█▋ | 33/200 [00:59<03:02, 1.09s/it]\n 17%|█▋ | 34/200 [00:59<02:21, 1.17it/s]\n 18%|█▊ | 35/200 [00:59<01:52, 1.46it/s]\n 18%|█▊ | 36/200 [01:03<04:06, 1.50s/it]\n 18%|█▊ | 37/200 [01:06<05:36, 2.06s/it]\n 19%|█▉ | 38/200 [01:10<06:42, 2.48s/it]\n 20%|█▉ | 39/200 [01:10<04:54, 1.83s/it]\n 20%|██ | 40/200 [01:13<06:08, 2.31s/it]\n 20%|██ | 41/200 [01:17<06:56, 2.62s/it]\n 21%|██ | 42/200 [01:20<07:36, 2.89s/it]\n 22%|██▏ | 43/200 [01:21<05:31, 2.11s/it]\n 22%|██▏ | 44/200 [01:24<06:28, 2.49s/it]\n 22%|██▎ | 45/200 [01:24<04:36, 1.78s/it]\n 23%|██▎ | 46/200 [01:24<03:24, 1.33s/it]\n 24%|██▎ | 47/200 [01:25<02:35, 1.02s/it]\n 24%|██▍ | 48/200 [01:28<04:20, 1.71s/it]\n 24%|██▍ | 49/200 [01:31<05:37, 2.24s/it]\n 25%|██▌ | 50/200 [01:32<04:07, 1.65s/it]\n 26%|██▌ | 51/200 [01:35<05:23, 2.17s/it]\n 26%|██▌ | 52/200 [01:38<06:14, 2.53s/it]\n 26%|██▋ | 53/200 [01:39<04:32, 1.85s/it]\n 27%|██▋ | 54/200 [01:39<03:22, 1.39s/it]\n 28%|██▊ | 55/200 [01:42<04:49, 2.00s/it]\n 28%|██▊ | 56/200 [01:43<03:33, 1.48s/it]\n 28%|██▊ | 57/200 [01:46<04:55, 2.07s/it]\n 29%|██▉ | 58/200 [01:50<05:50, 2.47s/it]\n 30%|██▉ | 59/200 [01:53<06:27, 2.75s/it]\n 30%|███ | 60/200 [01:53<04:40, 2.01s/it]\n 30%|███ | 61/200 [01:54<03:27, 1.49s/it]\n 31%|███ | 62/200 [01:57<04:44, 2.06s/it]\n 32%|███▏ | 63/200 [02:00<05:37, 2.46s/it]\n 32%|███▏ | 64/200 [02:04<06:11, 2.73s/it]\n 32%|███▎ | 65/200 [02:04<04:30, 2.01s/it]\n 33%|███▎ | 66/200 [02:04<03:13, 1.44s/it]\n 34%|███▎ | 67/200 [02:07<04:27, 2.01s/it]\n 34%|███▍ | 68/200 [02:08<03:17, 1.49s/it]\n 34%|███▍ | 69/200 [02:11<04:35, 2.10s/it]\n 35%|███▌ | 70/200 [02:11<03:16, 1.51s/it]\n 36%|███▌ | 71/200 [02:15<04:26, 2.06s/it]\n 36%|███▌ | 72/200 [02:15<03:15, 1.52s/it]\n 36%|███▋ | 73/200 [02:18<04:26, 2.10s/it]\n 37%|███▋ | 74/200 [02:19<03:09, 1.51s/it]\n 38%|███▊ | 75/200 [02:19<02:22, 1.14s/it]\n 38%|███▊ | 76/200 [02:22<03:44, 1.81s/it]\n 38%|███▊ | 77/200 [02:26<04:47, 2.33s/it]\n 39%|███▉ | 78/200 [02:26<03:23, 1.67s/it]\n 40%|███▉ | 79/200 [02:26<02:32, 1.26s/it]\n 40%|████ | 80/200 [02:30<03:45, 1.88s/it]\n 40%|████ | 81/200 [02:30<02:45, 1.39s/it]\n 41%|████ | 82/200 [02:33<03:55, 1.99s/it]\n 42%|████▏ | 83/200 [02:33<02:52, 1.48s/it]\n 42%|████▏ | 84/200 [02:37<04:03, 2.10s/it]\n 42%|████▎ | 85/200 [02:40<04:45, 2.48s/it]\n 43%|████▎ | 86/200 [02:44<05:12, 2.74s/it]\n 44%|████▎ | 87/200 [02:44<03:41, 1.96s/it]\n 44%|████▍ | 88/200 [02:47<04:25, 2.37s/it]\n 44%|████▍ | 89/200 [02:51<05:02, 2.73s/it]\n 45%|████▌ | 90/200 [02:51<03:34, 1.95s/it]\n 46%|████▌ | 91/200 [02:51<02:38, 1.46s/it]\n 46%|████▌ | 92/200 [02:55<03:39, 2.03s/it]\n 46%|████▋ | 93/200 [02:55<02:40, 1.50s/it]\n 47%|████▋ | 94/200 [02:55<02:01, 1.15s/it]\n 48%|████▊ | 95/200 [02:59<03:09, 1.81s/it]\n 48%|████▊ | 96/200 [03:02<03:58, 2.30s/it]\n 48%|████▊ | 97/200 [03:05<04:33, 2.65s/it]\n 49%|████▉ | 98/200 [03:09<04:51, 2.86s/it]\n 50%|████▉ | 99/200 [03:12<05:05, 3.02s/it]\n 50%|█████ | 100/200 [03:12<03:39, 2.19s/it]\n 50%|█████ | 101/200 [03:16<04:18, 2.61s/it]\n 51%|█████ | 102/200 [03:16<03:02, 1.87s/it]\n 52%|█████▏ | 103/200 [03:20<03:45, 2.33s/it]\n 52%|█████▏ | 104/200 [03:23<04:20, 2.71s/it]\n 52%|█████▎ | 105/200 [03:26<04:32, 2.87s/it]\n 53%|█████▎ | 106/200 [03:27<03:16, 2.09s/it]\n 54%|█████▎ | 107/200 [03:27<02:23, 1.55s/it]\n 54%|█████▍ | 108/200 [03:27<01:47, 1.17s/it]\n 55%|█████▍ | 109/200 [03:28<01:22, 1.10it/s]\n 55%|█████▌ | 110/200 [03:31<02:30, 1.67s/it]\n 56%|█████▌ | 111/200 [03:31<01:51, 1.25s/it]\n 56%|█████▌ | 112/200 [03:35<02:48, 1.92s/it]\n 56%|█████▋ | 113/200 [03:38<03:25, 2.36s/it]\n 57%|█████▋ | 114/200 [03:38<02:28, 1.73s/it]\n 57%|█████▊ | 115/200 [03:39<01:51, 1.31s/it]\n 58%|█████▊ | 116/200 [03:39<01:24, 1.00s/it]\n 58%|█████▊ | 117/200 [03:39<01:01, 1.35it/s]\n 59%|█████▉ | 118/200 [03:39<00:49, 1.65it/s]\n 60%|█████▉ | 119/200 [03:40<00:40, 1.98it/s]\n 60%|██████ | 120/200 [03:40<00:35, 2.28it/s]\n 60%|██████ | 121/200 [03:40<00:30, 2.56it/s]\n 61%|██████ | 122/200 [03:44<01:41, 1.30s/it]\n 62%|██████▏ | 123/200 [03:44<01:16, 1.01it/s]\n 62%|██████▏ | 124/200 [03:44<00:59, 1.27it/s]\n 62%|██████▎ | 125/200 [03:45<00:47, 1.57it/s]\n 63%|██████▎ | 126/200 [03:48<01:49, 1.48s/it]\n 64%|██████▎ | 127/200 [03:51<02:29, 2.05s/it]\n 64%|██████▍ | 128/200 [03:52<01:49, 1.52s/it]\n 64%|██████▍ | 129/200 [03:55<02:28, 2.10s/it]\n 65%|██████▌ | 130/200 [03:58<02:53, 2.48s/it]\n 66%|██████▌ | 131/200 [03:59<02:06, 1.84s/it]\n 66%|██████▌ | 132/200 [04:02<02:36, 2.31s/it]\n 66%|██████▋ | 133/200 [04:02<01:50, 1.65s/it]\n 67%|██████▋ | 134/200 [04:03<01:21, 1.24s/it]\n 68%|██████▊ | 135/200 [04:06<02:02, 1.88s/it]\n 68%|██████▊ | 136/200 [04:06<01:29, 1.40s/it]\n 68%|██████▊ | 137/200 [04:07<01:07, 1.08s/it]\n 69%|██████▉ | 138/200 [04:10<01:49, 1.76s/it]\n 70%|██████▉ | 139/200 [04:10<01:20, 1.32s/it]\n 70%|███████ | 140/200 [04:14<01:57, 1.96s/it]\n 70%|███████ | 141/200 [04:14<01:26, 1.46s/it]\n 71%|███████ | 142/200 [04:17<01:59, 2.05s/it]\n 72%|███████▏ | 143/200 [04:21<02:19, 2.45s/it]\n 72%|███████▏ | 144/200 [04:21<01:40, 1.80s/it]\n 72%|███████▎ | 145/200 [04:21<01:14, 1.36s/it]\n 73%|███████▎ | 146/200 [04:25<01:48, 2.01s/it]\n 74%|███████▎ | 147/200 [04:28<02:08, 2.42s/it]\n 74%|███████▍ | 148/200 [04:28<01:30, 1.73s/it]\n 74%|███████▍ | 149/200 [04:32<01:55, 2.27s/it]\n 75%|███████▌ | 150/200 [04:32<01:21, 1.63s/it]\n 76%|███████▌ | 151/200 [04:32<01:00, 1.23s/it]\n 76%|███████▌ | 152/200 [04:33<00:45, 1.05it/s]\n 76%|███████▋ | 153/200 [04:36<01:19, 1.69s/it]\n 77%|███████▋ | 154/200 [04:39<01:40, 2.18s/it]\n 78%|███████▊ | 155/200 [04:43<01:54, 2.54s/it]\n 78%|███████▊ | 156/200 [04:46<02:04, 2.84s/it]\n 78%|███████▊ | 157/200 [04:50<02:08, 2.99s/it]\n 79%|███████▉ | 158/200 [04:53<02:10, 3.11s/it]\n 80%|███████▉ | 159/200 [04:53<01:30, 2.21s/it]\n 80%|████████ | 160/200 [04:57<01:44, 2.61s/it]\n 80%|████████ | 161/200 [05:00<01:50, 2.83s/it]\n 81%|████████ | 162/200 [05:00<01:16, 2.02s/it]\n 82%|████████▏ | 163/200 [05:01<00:55, 1.49s/it]\n 82%|████████▏ | 164/200 [05:01<00:40, 1.13s/it]\n 82%|████████▎ | 165/200 [05:04<01:03, 1.81s/it]\n 83%|████████▎ | 166/200 [05:04<00:45, 1.35s/it]\n 84%|████████▎ | 167/200 [05:08<01:05, 1.98s/it]\n 84%|████████▍ | 168/200 [05:11<01:17, 2.41s/it]\n 84%|████████▍ | 169/200 [05:15<01:23, 2.69s/it]\n 85%|████████▌ | 170/200 [05:15<00:58, 1.96s/it]\n 86%|████████▌ | 171/200 [05:18<01:09, 2.38s/it]\n 86%|████████▌ | 172/200 [05:22<01:14, 2.67s/it]\n 86%|████████▋ | 173/200 [05:25<01:18, 2.90s/it]\n 87%|████████▋ | 174/200 [05:28<01:18, 3.03s/it]\n 88%|████████▊ | 175/200 [05:32<01:18, 3.12s/it]\n 88%|████████▊ | 176/200 [05:35<01:16, 3.20s/it]\n 88%|████████▊ | 177/200 [05:35<00:53, 2.32s/it]\n 89%|████████▉ | 178/200 [05:39<00:57, 2.62s/it]\n 90%|████████▉ | 179/200 [05:42<01:00, 2.89s/it]\n 90%|█████████ | 180/200 [05:46<01:00, 3.02s/it]\n 90%|█████████ | 181/200 [05:46<00:40, 2.15s/it]\n 91%|█████████ | 182/200 [05:46<00:28, 1.59s/it]\n 92%|█████████▏| 183/200 [05:46<00:20, 1.20s/it]\n 92%|█████████▏| 184/200 [05:47<00:14, 1.08it/s]\n 92%|█████████▎| 185/200 [05:50<00:24, 1.65s/it]\n 93%|█████████▎| 186/200 [05:53<00:30, 2.16s/it]\n 94%|█████████▎| 187/200 [05:57<00:32, 2.52s/it]\n 94%|█████████▍| 188/200 [05:57<00:22, 1.84s/it]\n 94%|█████████▍| 189/200 [05:57<00:15, 1.37s/it]\n 95%|█████████▌| 190/200 [06:01<00:19, 2.00s/it]\n 96%|█████████▌| 191/200 [06:01<00:13, 1.48s/it]\n 96%|█████████▌| 192/200 [06:01<00:09, 1.13s/it]\n 96%|█████████▋| 193/200 [06:01<00:06, 1.13it/s]\n 97%|█████████▋| 194/200 [06:05<00:09, 1.64s/it]\n 98%|█████████▊| 195/200 [06:08<00:10, 2.17s/it]\n 98%|█████████▊| 196/200 [06:08<00:06, 1.56s/it]\n 98%|█████████▊| 197/200 [06:12<00:06, 2.13s/it]\n 99%|█████████▉| 198/200 [06:15<00:04, 2.50s/it]\n100%|█████████▉| 199/200 [06:19<00:02, 2.76s/it]\n100%|██████████| 200/200 [06:19<00:00, 1.97s/it]\n100%|██████████| 200/200 [06:19<00:00, 1.90s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1752859283/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_1752859283/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_1752859283/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_1752859283/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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : 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 (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 : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : 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 : 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"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 379.25691318511963\nerrors 96\nmean length: 1.56\n\nthroughput (request / second): 0.5273470121357491\nthroughput (character / second): 0.8226613389317685\naverage request duration (s) 1.896173985004425\n50%ile request duration (s) 3.311178684234619\n75%ile request duration (s) 3.3995442986488342\n90%ile request duration (s) 3.4644717693328855\n95%ile request duration (s) 3.5330334305763245\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-llama31-mer-v2-t-44570-v2-profiler is running
Tearing down inference service chaiml-llama31-mer-v2-t-44570-v2-profiler
Service chaiml-llama31-mer-v2-t-44570-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.06s
Shutdown handler de-registered
chaiml-llama31-mer-v2-t_44570_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama31-mer-v2-t_44570_v2 status is now torndown due to DeploymentManager action
chaiml-llama31-mer-v2-t_44570_v2 status is now torndown due to DeploymentManager action