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-llama8b-retune7-90738-v1-mkmlizer
Waiting for job on chaiml-llama8b-retune7-90738-v1-mkmlizer to finish
chaiml-llama8b-retune7-90738-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Version: 0.29.3 ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ belonging to: ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ║ ║
chaiml-llama8b-retune7-90738-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama8b-retune7-90738-v1-mkmlizer: Downloaded to shared memory in 27.519s
chaiml-llama8b-retune7-90738-v1-mkmlizer: Checking if ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512-try2 already exists in ChaiML
chaiml-llama8b-retune7-90738-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp0dq0bar2, device:0
chaiml-llama8b-retune7-90738-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama8b-retune7-90738-v1-mkmlizer: quantized model in 19.820s
chaiml-llama8b-retune7-90738-v1-mkmlizer: Processed model ChaiML/llama8b-retune7-rm-pointwise-datav1-900k-1e-64mckpt-newlinfull-seq512-try2 in 47.340s
chaiml-llama8b-retune7-90738-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama8b-retune7-90738-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama8b-retune7-90738-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1
chaiml-llama8b-retune7-90738-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1/config.json
chaiml-llama8b-retune7-90738-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1/special_tokens_map.json
chaiml-llama8b-retune7-90738-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1/tokenizer_config.json
chaiml-llama8b-retune7-90738-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1/tokenizer.json
chaiml-llama8b-retune7-90738-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama8b-retune7-90738-v1/flywheel_model.0.safetensors
Job chaiml-llama8b-retune7-90738-v1-mkmlizer completed after 73.83s with status: succeeded
Stopping job with name chaiml-llama8b-retune7-90738-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama8b-retune7-90738-v1
Waiting for inference service chaiml-llama8b-retune7-90738-v1 to be ready
Failed to get response for submission blend_doson_2025-06-17: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-llama8b-retune7-90738-v1 ready after 120.4440450668335s
Pipeline stage MKMLDeployer completed in 121.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.271367788314819s
Received healthy response to inference request in 3.142549753189087s
Received healthy response to inference request in 2.939021348953247s
Received healthy response to inference request in 5.847868204116821s
Received healthy response to inference request in 3.03214168548584s
5 requests
0 failed requests
5th percentile: 2.9576454162597656
10th percentile: 2.976269483566284
20th percentile: 3.0135176181793213
30th percentile: 3.0542232990264893
40th percentile: 3.098386526107788
50th percentile: 3.142549753189087
60th percentile: 3.59407696723938
70th percentile: 4.045604181289673
80th percentile: 4.58666787147522
90th percentile: 5.21726803779602
95th percentile: 5.53256812095642
99th percentile: 5.7848081874847415
mean time: 3.846589756011963
Pipeline stage StressChecker completed in 20.50s
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 0.73s
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 1.07s
Shutdown handler de-registered
chaiml-llama8b-retune7-_90738_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama8b-retune7-90738-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-90738-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-90738-v1-profiler ready after 121.22305846214294s
Pipeline stage MKMLProfilerDeployer completed in 122.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk:/code/chaiverse_profiler_1750702649 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750702649 && 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_1750702649/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk:/code/chaiverse_profiler_1750703053 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750703053 && 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_1750703053/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk:/code/chaiverse_profiler_1750703478 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplozbffk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750703478 && 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_1750703478/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<10:58, 3.31s/it]\n 1%| | 2/200 [00:06<11:05, 3.36s/it]\n 2%|▏ | 3/200 [00:06<06:11, 1.89s/it]\n 2%|▏ | 4/200 [00:07<04:07, 1.26s/it]\n 2%|▎ | 5/200 [00:07<02:57, 1.10it/s]\n 3%|▎ | 6/200 [00:10<05:41, 1.76s/it]\n 4%|▎ | 7/200 [00:11<04:04, 1.27s/it]\n 4%|▍ | 8/200 [00:14<06:08, 1.92s/it]\n 4%|▍ | 9/200 [00:14<04:26, 1.40s/it]\n 5%|▌ | 10/200 [00:14<03:19, 1.05s/it]\n 6%|▌ | 11/200 [00:18<05:36, 1.78s/it]\n 6%|▌ | 12/200 [00:21<07:08, 2.28s/it]\n 6%|▋ | 13/200 [00:25<08:06, 2.60s/it]\n 7%|▋ | 14/200 [00:25<05:44, 1.85s/it]\n 8%|▊ | 15/200 [00:28<07:19, 2.37s/it]\n 8%|▊ | 16/200 [00:32<08:00, 2.61s/it]\n 8%|▊ | 17/200 [00:35<08:36, 2.82s/it]\n 9%|▉ | 18/200 [00:38<09:13, 3.04s/it]\n 10%|▉ | 19/200 [00:38<06:32, 2.17s/it]\n 10%|█ | 20/200 [00:42<07:40, 2.56s/it]\n 10%|█ | 21/200 [00:42<05:28, 1.83s/it]\n 11%|█ | 22/200 [00:42<04:02, 1.36s/it]\n 12%|█▏ | 23/200 [00:46<05:49, 1.97s/it]\n 12%|█▏ | 24/200 [00:46<04:16, 1.46s/it]\n 12%|█▎ | 25/200 [00:46<03:13, 1.11s/it]\n 13%|█▎ | 26/200 [00:50<05:17, 1.83s/it]\n 14%|█▎ | 27/200 [00:50<03:54, 1.35s/it]\n 14%|█▍ | 28/200 [00:53<05:35, 1.95s/it]\n 14%|█▍ | 29/200 [00:54<04:05, 1.44s/it]\n 15%|█▌ | 30/200 [00:54<03:05, 1.09s/it]\n 16%|█▌ | 31/200 [00:57<05:02, 1.79s/it]\n 16%|█▌ | 32/200 [00:58<03:43, 1.33s/it]\n 16%|█▋ | 33/200 [00:58<02:50, 1.02s/it]\n 17%|█▋ | 34/200 [00:58<02:13, 1.25it/s]\n 18%|█▊ | 35/200 [01:02<04:19, 1.57s/it]\n 18%|█▊ | 36/200 [01:02<03:14, 1.18s/it]\n 18%|█▊ | 37/200 [01:05<05:01, 1.85s/it]\n 19%|█▉ | 38/200 [01:06<03:43, 1.38s/it]\n 20%|█▉ | 39/200 [01:09<05:24, 2.01s/it]\n 20%|██ | 40/200 [01:09<03:58, 1.49s/it]\n 20%|██ | 41/200 [01:13<05:26, 2.05s/it]\n 21%|██ | 42/200 [01:13<03:52, 1.47s/it]\n 22%|██▏ | 43/200 [01:16<05:27, 2.08s/it]\n 22%|██▏ | 44/200 [01:16<03:53, 1.50s/it]\n 22%|██▎ | 45/200 [01:20<05:24, 2.09s/it]\n 23%|██▎ | 46/200 [01:23<06:19, 2.46s/it]\n 24%|██▎ | 47/200 [01:27<06:57, 2.73s/it]\n 24%|██▍ | 48/200 [01:27<04:57, 1.96s/it]\n 24%|██▍ | 49/200 [01:30<06:06, 2.43s/it]\n 25%|██▌ | 50/200 [01:34<06:45, 2.71s/it]\n 26%|██▌ | 51/200 [01:34<04:47, 1.93s/it]\n 26%|██▌ | 52/200 [01:34<03:31, 1.43s/it]\n 26%|██▋ | 53/200 [01:34<02:39, 1.09s/it]\n 27%|██▋ | 54/200 [01:38<04:19, 1.77s/it]\n 28%|██▊ | 55/200 [01:41<05:28, 2.26s/it]\n 28%|██▊ | 56/200 [01:41<03:58, 1.66s/it]\n 28%|██▊ | 57/200 [01:42<02:58, 1.25s/it]\n 29%|██▉ | 58/200 [01:42<02:15, 1.05it/s]\n 30%|██▉ | 59/200 [01:42<01:45, 1.34it/s]\n 30%|███ | 60/200 [01:42<01:24, 1.66it/s]\n 30%|███ | 61/200 [01:43<01:03, 2.18it/s]\n 31%|███ | 62/200 [01:43<00:55, 2.49it/s]\n 32%|███▏ | 63/200 [01:43<00:48, 2.80it/s]\n 32%|███▏ | 64/200 [01:46<02:50, 1.26s/it]\n 32%|███▎ | 65/200 [01:50<04:19, 1.92s/it]\n 33%|███▎ | 66/200 [01:50<03:10, 1.42s/it]\n 34%|███▎ | 67/200 [01:54<04:27, 2.01s/it]\n 34%|███▍ | 68/200 [01:54<03:15, 1.48s/it]\n 34%|███▍ | 69/200 [01:54<02:25, 1.11s/it]\n 35%|███▌ | 70/200 [01:57<03:53, 1.79s/it]\n 36%|███▌ | 71/200 [02:01<04:52, 2.27s/it]\n 36%|███▌ | 72/200 [02:04<05:29, 2.58s/it]\n 36%|███▋ | 73/200 [02:07<05:56, 2.81s/it]\n 37%|███▋ | 74/200 [02:08<04:17, 2.04s/it]\n 38%|███▊ | 75/200 [02:08<03:09, 1.51s/it]\n 38%|███▊ | 76/200 [02:11<04:17, 2.08s/it]\n 38%|███▊ | 77/200 [02:15<05:05, 2.49s/it]\n 39%|███▉ | 78/200 [02:15<03:41, 1.81s/it]\n 40%|███▉ | 79/200 [02:15<02:43, 1.35s/it]\n 40%|████ | 80/200 [02:16<02:04, 1.04s/it]\n 40%|████ | 81/200 [02:19<03:28, 1.75s/it]\n 41%|████ | 82/200 [02:22<04:23, 2.24s/it]\n 42%|████▏ | 83/200 [02:26<05:00, 2.57s/it]\n 42%|████▏ | 84/200 [02:29<05:26, 2.81s/it]\n 42%|████▎ | 85/200 [02:29<03:51, 2.01s/it]\n 43%|████▎ | 86/200 [02:30<02:49, 1.49s/it]\n 44%|████▎ | 87/200 [02:30<02:07, 1.12s/it]\n 44%|████▍ | 88/200 [02:33<03:20, 1.79s/it]\n 44%|████▍ | 89/200 [02:36<04:09, 2.25s/it]\n 45%|████▌ | 90/200 [02:40<04:49, 2.64s/it]\n 46%|████▌ | 91/200 [02:43<05:10, 2.85s/it]\n 46%|████▌ | 92/200 [02:47<05:23, 3.00s/it]\n 46%|████▋ | 93/200 [02:47<03:48, 2.14s/it]\n 47%|████▋ | 94/200 [02:50<04:33, 2.58s/it]\n 48%|████▊ | 95/200 [02:54<04:56, 2.82s/it]\n 48%|████▊ | 96/200 [02:57<05:11, 2.99s/it]\n 48%|████▊ | 97/200 [03:01<05:23, 3.14s/it]\n 49%|████▉ | 98/200 [03:04<05:23, 3.18s/it]\n 50%|████▉ | 99/200 [03:04<03:52, 2.30s/it]\n 50%|█████ | 100/200 [03:08<04:22, 2.62s/it]\n 50%|█████ | 101/200 [03:08<03:09, 1.91s/it]\n 51%|█████ | 102/200 [03:11<03:52, 2.37s/it]\n 52%|█████▏ | 103/200 [03:12<02:48, 1.73s/it]\n 52%|█████▏ | 104/200 [03:15<03:32, 2.22s/it]\n 52%|█████▎ | 105/200 [03:18<04:06, 2.60s/it]\n 53%|█████▎ | 106/200 [03:18<02:54, 1.86s/it]\n 54%|█████▎ | 107/200 [03:22<03:34, 2.31s/it]\n 54%|█████▍ | 108/200 [03:25<04:03, 2.65s/it]\n 55%|█████▍ | 109/200 [03:29<04:20, 2.86s/it]\n 55%|█████▌ | 110/200 [03:32<04:33, 3.04s/it]\n 56%|█████▌ | 111/200 [03:35<04:38, 3.13s/it]\n 56%|█████▌ | 112/200 [03:36<03:16, 2.24s/it]\n 56%|█████▋ | 113/200 [03:39<03:48, 2.62s/it]\n 57%|█████▋ | 114/200 [03:39<02:41, 1.88s/it]\n 57%|█████▊ | 115/200 [03:43<03:21, 2.37s/it]\n 58%|█████▊ | 116/200 [03:46<03:44, 2.67s/it]\n 58%|█████▊ | 117/200 [03:49<03:56, 2.85s/it]\n 59%|█████▉ | 118/200 [03:50<02:50, 2.07s/it]\n 60%|█████▉ | 119/200 [03:50<02:04, 1.53s/it]\n 60%|██████ | 120/200 [03:53<02:47, 2.10s/it]\n 60%|██████ | 121/200 [03:57<03:13, 2.45s/it]\n 61%|██████ | 122/200 [03:57<02:19, 1.79s/it]\n 62%|██████▏ | 123/200 [04:00<02:57, 2.30s/it]\n 62%|██████▏ | 124/200 [04:01<02:08, 1.69s/it]\n 62%|██████▎ | 125/200 [04:01<01:34, 1.26s/it]\n 63%|██████▎ | 126/200 [04:04<02:18, 1.87s/it]\n 64%|██████▎ | 127/200 [04:04<01:41, 1.38s/it]\n 64%|██████▍ | 128/200 [04:05<01:15, 1.05s/it]\n 64%|██████▍ | 129/200 [04:05<00:57, 1.23it/s]\n 65%|██████▌ | 130/200 [04:08<01:50, 1.58s/it]\n 66%|██████▌ | 131/200 [04:12<02:26, 2.13s/it]\n 66%|██████▌ | 132/200 [04:12<01:46, 1.57s/it]\n 66%|██████▋ | 133/200 [04:12<01:18, 1.18s/it]\n 67%|██████▋ | 134/200 [04:16<02:01, 1.84s/it]\n 68%|██████▊ | 135/200 [04:16<01:28, 1.36s/it]\n 68%|██████▊ | 136/200 [04:19<02:06, 1.98s/it]\n 68%|██████▊ | 137/200 [04:19<01:29, 1.43s/it]\n 69%|██████▉ | 138/200 [04:23<02:07, 2.06s/it]\n 70%|██████▉ | 139/200 [04:23<01:30, 1.48s/it]\n 70%|███████ | 140/200 [04:27<02:05, 2.09s/it]\n 70%|███████ | 141/200 [04:27<01:28, 1.51s/it]\n 71%|███████ | 142/200 [04:27<01:06, 1.14s/it]\n 72%|███████▏ | 143/200 [04:30<01:43, 1.81s/it]\n 72%|███████▏ | 144/200 [04:34<02:07, 2.27s/it]\n 72%|███████▎ | 145/200 [04:34<01:31, 1.66s/it]\n 73%|███████▎ | 146/200 [04:38<01:59, 2.22s/it]\n 74%|███████▎ | 147/200 [04:41<02:15, 2.55s/it]\n 74%|███████▍ | 148/200 [04:41<01:35, 1.83s/it]\n 74%|███████▍ | 149/200 [04:44<01:56, 2.28s/it]\n 75%|███████▌ | 150/200 [04:48<02:10, 2.60s/it]\n 76%|███████▌ | 151/200 [04:51<02:21, 2.89s/it]\n 76%|███████▌ | 152/200 [04:51<01:38, 2.06s/it]\n 76%|███████▋ | 153/200 [04:55<01:56, 2.48s/it]\n 77%|███████▋ | 154/200 [04:58<02:05, 2.73s/it]\n 78%|███████▊ | 155/200 [05:02<02:11, 2.93s/it]\n 78%|███████▊ | 156/200 [05:02<01:32, 2.09s/it]\n 78%|███████▊ | 157/200 [05:02<01:06, 1.55s/it]\n 79%|███████▉ | 158/200 [05:02<00:48, 1.16s/it]\n 80%|███████▉ | 159/200 [05:03<00:36, 1.12it/s]\n 80%|████████ | 160/200 [05:03<00:28, 1.42it/s]\n 80%|████████ | 161/200 [05:06<00:58, 1.49s/it]\n 81%|████████ | 162/200 [05:10<01:18, 2.07s/it]\n 82%|████████▏ | 163/200 [05:13<01:31, 2.47s/it]\n 82%|████████▏ | 164/200 [05:13<01:04, 1.80s/it]\n 82%|████████▎ | 165/200 [05:13<00:46, 1.34s/it]\n 83%|████████▎ | 166/200 [05:17<01:06, 1.95s/it]\n 84%|████████▎ | 167/200 [05:20<01:18, 2.39s/it]\n 84%|████████▍ | 168/200 [05:24<01:26, 2.70s/it]\n 84%|████████▍ | 169/200 [05:27<01:29, 2.89s/it]\n 85%|████████▌ | 170/200 [05:30<01:30, 3.03s/it]\n 86%|████████▌ | 171/200 [05:34<01:31, 3.16s/it]\n 86%|████████▌ | 172/200 [05:37<01:28, 3.17s/it]\n 86%|████████▋ | 173/200 [05:40<01:27, 3.25s/it]\n 87%|████████▋ | 174/200 [05:44<01:26, 3.32s/it]\n 88%|████████▊ | 175/200 [05:44<00:59, 2.36s/it]\n 88%|████████▊ | 176/200 [05:48<01:05, 2.73s/it]\n 88%|████████▊ | 177/200 [05:51<01:07, 2.94s/it]\n 89%|████████▉ | 178/200 [05:55<01:08, 3.09s/it]\n 90%|████████▉ | 179/200 [05:55<00:46, 2.20s/it]\n 90%|█████████ | 180/200 [05:58<00:51, 2.59s/it]\n 90%|█████████ | 181/200 [06:02<00:54, 2.84s/it]\n 91%|█████████ | 182/200 [06:05<00:54, 3.01s/it]\n 92%|█████████▏| 183/200 [06:05<00:36, 2.15s/it]\n 92%|█████████▏| 184/200 [06:09<00:40, 2.56s/it]\n 92%|█████████▎| 185/200 [06:12<00:42, 2.82s/it]\n 93%|█████████▎| 186/200 [06:15<00:41, 2.93s/it]\n 94%|█████████▎| 187/200 [06:15<00:27, 2.13s/it]\n 94%|█████████▍| 188/200 [06:16<00:18, 1.56s/it]\n 94%|█████████▍| 189/200 [06:19<00:23, 2.09s/it]\n 95%|█████████▌| 190/200 [06:19<00:15, 1.54s/it]\n 96%|█████████▌| 191/200 [06:20<00:10, 1.16s/it]\n 96%|█████████▌| 192/200 [06:20<00:07, 1.13it/s]\n 96%|█████████▋| 193/200 [06:20<00:04, 1.43it/s]\n 97%|█████████▋| 194/200 [06:24<00:09, 1.52s/it]\n 98%|█████████▊| 195/200 [06:24<00:05, 1.15s/it]\n 98%|█████████▊| 196/200 [06:27<00:07, 1.81s/it]\n 98%|█████████▊| 197/200 [06:30<00:06, 2.26s/it]\n 99%|█████████▉| 198/200 [06:34<00:05, 2.60s/it]\n100%|█████████▉| 199/200 [06:37<00:02, 2.82s/it]\n100%|██████████| 200/200 [06:41<00:00, 2.98s/it]\n100%|██████████| 200/200 [06:41<00:00, 2.01s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1750703478/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_1750703478/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_1750703478/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_1750703478/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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : 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 (0,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 401.0607497692108\nerrors 88\nmean length: 1.68\n\nthroughput (request / second): 0.4986775697075552\nthroughput (character / second): 0.8377783171086928\naverage request duration (s) 2.0051936280727385\n50%ile request duration (s) 3.3212350606918335\n75%ile request duration (s) 3.4031172394752502\n90%ile request duration (s) 3.4786209583282472\n95%ile request duration (s) 3.519434094429016\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-llama8b-retune7-90738-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-90738-v1-profiler
Service chaiml-llama8b-retune7-90738-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.29s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-90738-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.55s
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-llama8b-retune7-90738-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-90738-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-90738-v1-profiler ready after 121.46641969680786s
Pipeline stage MKMLProfilerDeployer completed in 122.42s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6:/code/chaiverse_profiler_1750704083 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750704083 && 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_1750704083/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6:/code/chaiverse_profiler_1750704524 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750704524 && 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_1750704524/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6:/code/chaiverse_profiler_1750704936 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok4pd6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750704936 && 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_1750704936/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<11:26, 3.45s/it]\n 1%| | 2/200 [00:03<04:56, 1.50s/it]\n 2%|▏ | 3/200 [00:07<07:49, 2.38s/it]\n 2%|▏ | 4/200 [00:10<09:16, 2.84s/it]\n 2%|▎ | 5/200 [00:14<09:59, 3.08s/it]\n 3%|▎ | 6/200 [00:14<06:42, 2.07s/it]\n 4%|▎ | 7/200 [00:14<04:45, 1.48s/it]\n 4%|▍ | 8/200 [00:17<06:47, 2.12s/it]\n 4%|▍ | 9/200 [00:21<08:05, 2.54s/it]\n 5%|▌ | 10/200 [00:21<05:41, 1.80s/it]\n 6%|▌ | 11/200 [00:25<07:17, 2.31s/it]\n 6%|▌ | 12/200 [00:25<05:16, 1.68s/it]\n 6%|▋ | 13/200 [00:25<03:56, 1.27s/it]\n 7%|▋ | 14/200 [00:28<05:55, 1.91s/it]\n 8%|▊ | 15/200 [00:29<04:20, 1.41s/it]\n 8%|▊ | 16/200 [00:29<03:15, 1.06s/it]\n 8%|▊ | 17/200 [00:29<02:30, 1.22it/s]\n 9%|▉ | 18/200 [00:33<04:55, 1.63s/it]\n 10%|▉ | 19/200 [00:33<03:40, 1.22s/it]\n 10%|█ | 20/200 [00:36<05:38, 1.88s/it]\n 10%|█ | 21/200 [00:40<06:56, 2.33s/it]\n 11%|█ | 22/200 [00:43<07:57, 2.68s/it]\n 12%|█▏ | 23/200 [00:47<08:37, 2.93s/it]\n 12%|█▏ | 24/200 [00:50<09:01, 3.08s/it]\n 12%|█▎ | 25/200 [00:54<09:24, 3.23s/it]\n 13%|█▎ | 26/200 [00:57<09:27, 3.26s/it]\n 14%|█▎ | 27/200 [00:57<06:48, 2.36s/it]\n 14%|█▍ | 28/200 [01:01<07:46, 2.71s/it]\n 14%|█▍ | 29/200 [01:04<08:22, 2.94s/it]\n 15%|█▌ | 30/200 [01:05<05:55, 2.09s/it]\n 16%|█▌ | 31/200 [01:08<06:57, 2.47s/it]\n 16%|█▌ | 32/200 [01:11<07:48, 2.79s/it]\n 16%|█▋ | 33/200 [01:12<05:32, 1.99s/it]\n 17%|█▋ | 34/200 [01:15<06:48, 2.46s/it]\n 18%|█▊ | 35/200 [01:18<07:30, 2.73s/it]\n 18%|█▊ | 36/200 [01:19<05:19, 1.95s/it]\n 18%|█▊ | 37/200 [01:19<03:55, 1.45s/it]\n 19%|█▉ | 38/200 [01:22<05:30, 2.04s/it]\n 20%|█▉ | 39/200 [01:26<06:38, 2.47s/it]\n 20%|██ | 40/200 [01:29<07:17, 2.73s/it]\n 20%|██ | 41/200 [01:33<07:53, 2.98s/it]\n 21%|██ | 42/200 [01:36<08:13, 3.12s/it]\n 22%|██▏ | 43/200 [01:39<08:22, 3.20s/it]\n 22%|██▏ | 44/200 [01:40<05:55, 2.28s/it]\n 22%|██▎ | 45/200 [01:40<04:19, 1.68s/it]\n 23%|██▎ | 46/200 [01:43<05:41, 2.22s/it]\n 24%|██▎ | 47/200 [01:47<06:36, 2.59s/it]\n 24%|██▍ | 48/200 [01:50<07:16, 2.87s/it]\n 24%|██▍ | 49/200 [01:54<07:41, 3.06s/it]\n 25%|██▌ | 50/200 [01:57<07:55, 3.17s/it]\n 26%|██▌ | 51/200 [02:01<08:00, 3.23s/it]\n 26%|██▌ | 52/200 [02:01<05:40, 2.30s/it]\n 26%|██▋ | 53/200 [02:01<04:07, 1.69s/it]\n 27%|██▋ | 54/200 [02:01<03:03, 1.26s/it]\n 28%|██▊ | 55/200 [02:02<02:20, 1.03it/s]\n 28%|██▊ | 56/200 [02:02<01:49, 1.32it/s]\n 28%|██▊ | 57/200 [02:02<01:28, 1.61it/s]\n 29%|██▉ | 58/200 [02:02<01:14, 1.91it/s]\n 30%|██▉ | 59/200 [02:03<01:04, 2.19it/s]\n 30%|███ | 60/200 [02:06<03:12, 1.38s/it]\n 30%|███ | 61/200 [02:10<04:35, 1.98s/it]\n 31%|███ | 62/200 [02:13<05:32, 2.41s/it]\n 32%|███▏ | 63/200 [02:13<03:56, 1.73s/it]\n 32%|███▏ | 64/200 [02:14<02:56, 1.30s/it]\n 32%|███▎ | 65/200 [02:17<04:27, 1.98s/it]\n 33%|███▎ | 66/200 [02:20<05:23, 2.41s/it]\n 34%|███▎ | 67/200 [02:24<06:03, 2.73s/it]\n 34%|███▍ | 68/200 [02:27<06:27, 2.93s/it]\n 34%|███▍ | 69/200 [02:31<06:44, 3.09s/it]\n 35%|███▌ | 70/200 [02:31<04:46, 2.20s/it]\n 36%|███▌ | 71/200 [02:35<05:39, 2.63s/it]\n 36%|███▌ | 72/200 [02:38<06:06, 2.86s/it]\n 36%|███▋ | 73/200 [02:38<04:18, 2.04s/it]\n 37%|███▋ | 74/200 [02:42<05:09, 2.45s/it]\n 38%|███▊ | 75/200 [02:45<05:52, 2.82s/it]\n 38%|███▊ | 76/200 [02:49<06:12, 3.00s/it]\n 38%|███▊ | 77/200 [02:52<06:26, 3.14s/it]\n 39%|███▉ | 78/200 [02:52<04:32, 2.23s/it]\n 40%|███▉ | 79/200 [02:53<03:19, 1.65s/it]\n 40%|████ | 80/200 [02:56<04:21, 2.18s/it]\n 40%|████ | 81/200 [02:59<05:05, 2.57s/it]\n 41%|████ | 82/200 [03:00<03:40, 1.87s/it]\n 42%|████▏ | 83/200 [03:00<02:42, 1.39s/it]\n 42%|████▏ | 84/200 [03:03<03:52, 2.00s/it]\n 42%|████▎ | 85/200 [03:04<02:49, 1.48s/it]\n 43%|████▎ | 86/200 [03:07<03:54, 2.06s/it]\n 44%|████▎ | 87/200 [03:07<02:50, 1.51s/it]\n 44%|████▍ | 88/200 [03:11<03:54, 2.09s/it]\n 44%|████▍ | 89/200 [03:11<02:50, 1.53s/it]\n 45%|████▌ | 90/200 [03:15<03:57, 2.16s/it]\n 46%|████▌ | 91/200 [03:18<04:37, 2.55s/it]\n 46%|████▌ | 92/200 [03:18<03:17, 1.82s/it]\n 46%|████▋ | 93/200 [03:18<02:25, 1.36s/it]\n 47%|████▋ | 94/200 [03:19<01:49, 1.03s/it]\n 48%|████▊ | 95/200 [03:22<03:03, 1.75s/it]\n 48%|████▊ | 96/200 [03:22<02:14, 1.30s/it]\n 48%|████▊ | 97/200 [03:26<03:21, 1.95s/it]\n 49%|████▉ | 98/200 [03:26<02:27, 1.44s/it]\n 50%|████▉ | 99/200 [03:26<01:50, 1.09s/it]\n 50%|█████ | 100/200 [03:30<02:58, 1.79s/it]\n 50%|█████ | 101/200 [03:30<02:11, 1.32s/it]\n 51%|█████ | 102/200 [03:33<03:12, 1.96s/it]\n 52%|█████▏ | 103/200 [03:37<03:53, 2.41s/it]\n 52%|█████▏ | 104/200 [03:40<04:19, 2.71s/it]\n 52%|█████▎ | 105/200 [03:41<03:07, 1.97s/it]\n 53%|█████▎ | 106/200 [03:44<03:47, 2.42s/it]\n 54%|█████▎ | 107/200 [03:47<04:14, 2.74s/it]\n 54%|█████▍ | 108/200 [03:51<04:30, 2.94s/it]\n 55%|█████▍ | 109/200 [03:51<03:14, 2.14s/it]\n 55%|█████▌ | 110/200 [03:51<02:22, 1.58s/it]\n 56%|█████▌ | 111/200 [03:55<03:09, 2.13s/it]\n 56%|█████▌ | 112/200 [03:55<02:18, 1.58s/it]\n 56%|█████▋ | 113/200 [03:59<03:06, 2.14s/it]\n 57%|█████▋ | 114/200 [03:59<02:12, 1.54s/it]\n 57%|█████▊ | 115/200 [04:02<02:59, 2.11s/it]\n 58%|█████▊ | 116/200 [04:02<02:09, 1.55s/it]\n 58%|█████▊ | 117/200 [04:06<02:59, 2.17s/it]\n 59%|█████▉ | 118/200 [04:09<03:29, 2.55s/it]\n 60%|█████▉ | 119/200 [04:13<03:47, 2.81s/it]\n 60%|██████ | 120/200 [04:13<02:40, 2.00s/it]\n 60%|██████ | 121/200 [04:13<01:56, 1.48s/it]\n 61%|██████ | 122/200 [04:14<01:27, 1.12s/it]\n 62%|██████▏ | 123/200 [04:17<02:20, 1.83s/it]\n 62%|██████▏ | 124/200 [04:20<02:55, 2.31s/it]\n 62%|██████▎ | 125/200 [04:21<02:04, 1.66s/it]\n 63%|██████▎ | 126/200 [04:21<01:31, 1.24s/it]\n 64%|██████▎ | 127/200 [04:24<02:17, 1.89s/it]\n 64%|██████▍ | 128/200 [04:28<02:52, 2.40s/it]\n 64%|██████▍ | 129/200 [04:28<02:01, 1.72s/it]\n 65%|██████▌ | 130/200 [04:28<01:29, 1.28s/it]\n 66%|██████▌ | 131/200 [04:32<02:16, 1.98s/it]\n 66%|██████▌ | 132/200 [04:32<01:36, 1.42s/it]\n 66%|██████▋ | 133/200 [04:36<02:18, 2.06s/it]\n 67%|██████▋ | 134/200 [04:39<02:44, 2.49s/it]\n 68%|██████▊ | 135/200 [04:39<01:56, 1.79s/it]\n 68%|██████▊ | 136/200 [04:39<01:25, 1.33s/it]\n 68%|██████▊ | 137/200 [04:43<02:04, 1.98s/it]\n 69%|██████▉ | 138/200 [04:46<02:28, 2.40s/it]\n 70%|██████▉ | 139/200 [04:47<01:47, 1.75s/it]\n 70%|███████ | 140/200 [04:50<02:16, 2.27s/it]\n 70%|███████ | 141/200 [04:50<01:37, 1.66s/it]\n 71%|███████ | 142/200 [04:51<01:11, 1.24s/it]\n 72%|███████▏ | 143/200 [04:54<01:47, 1.88s/it]\n 72%|███████▏ | 144/200 [04:57<02:13, 2.38s/it]\n 72%|███████▎ | 145/200 [05:01<02:28, 2.70s/it]\n 73%|███████▎ | 146/200 [05:01<01:43, 1.93s/it]\n 74%|███████▎ | 147/200 [05:01<01:15, 1.43s/it]\n 74%|███████▍ | 148/200 [05:05<01:45, 2.02s/it]\n 74%|███████▍ | 149/200 [05:08<02:07, 2.49s/it]\n 75%|███████▌ | 150/200 [05:12<02:15, 2.72s/it]\n 76%|███████▌ | 151/200 [05:15<02:24, 2.95s/it]\n 76%|███████▌ | 152/200 [05:15<01:40, 2.10s/it]\n 76%|███████▋ | 153/200 [05:19<01:59, 2.54s/it]\n 77%|███████▋ | 154/200 [05:22<02:09, 2.81s/it]\n 78%|███████▊ | 155/200 [05:22<01:30, 2.01s/it]\n 78%|███████▊ | 156/200 [05:23<01:05, 1.48s/it]\n 78%|███████▊ | 157/200 [05:26<01:28, 2.05s/it]\n 79%|███████▉ | 158/200 [05:26<01:03, 1.51s/it]\n 80%|███████▉ | 159/200 [05:30<01:25, 2.08s/it]\n 80%|████████ | 160/200 [05:30<01:01, 1.53s/it]\n 80%|████████ | 161/200 [05:33<01:21, 2.09s/it]\n 81%|████████ | 162/200 [05:33<00:58, 1.55s/it]\n 82%|████████▏ | 163/200 [05:37<01:18, 2.11s/it]\n 82%|████████▏ | 164/200 [05:40<01:30, 2.52s/it]\n 82%|████████▎ | 165/200 [05:44<01:36, 2.76s/it]\n 83%|████████▎ | 166/200 [05:44<01:08, 2.01s/it]\n 84%|████████▎ | 167/200 [05:44<00:49, 1.50s/it]\n 84%|████████▍ | 168/200 [05:48<01:07, 2.10s/it]\n 84%|████████▍ | 169/200 [05:51<01:17, 2.49s/it]\n 85%|████████▌ | 170/200 [05:51<00:54, 1.82s/it]\n 86%|████████▌ | 171/200 [05:52<00:39, 1.35s/it]\n 86%|████████▌ | 172/200 [05:55<00:54, 1.96s/it]\n 86%|████████▋ | 173/200 [05:55<00:39, 1.45s/it]\n 87%|████████▋ | 174/200 [05:59<00:53, 2.07s/it]\n 88%|████████▊ | 175/200 [05:59<00:37, 1.49s/it]\n 88%|████████▊ | 176/200 [06:03<00:50, 2.11s/it]\n 88%|████████▊ | 177/200 [06:03<00:34, 1.51s/it]\n 89%|████████▉ | 178/200 [06:06<00:45, 2.08s/it]\n 90%|████████▉ | 179/200 [06:06<00:32, 1.53s/it]\n 90%|█████████ | 180/200 [06:10<00:43, 2.16s/it]\n 90%|█████████ | 181/200 [06:13<00:48, 2.53s/it]\n 91%|█████████ | 182/200 [06:13<00:32, 1.81s/it]\n 92%|█████████▏| 183/200 [06:17<00:39, 2.32s/it]\n 92%|█████████▏| 184/200 [06:17<00:27, 1.70s/it]\n 92%|█████████▎| 185/200 [06:21<00:33, 2.27s/it]\n 93%|█████████▎| 186/200 [06:21<00:22, 1.62s/it]\n 94%|█████████▎| 187/200 [06:21<00:15, 1.21s/it]\n 94%|█████████▍| 188/200 [06:25<00:22, 1.89s/it]\n 94%|█████████▍| 189/200 [06:25<00:15, 1.39s/it]\n 95%|█████████▌| 190/200 [06:25<00:10, 1.06s/it]\n 96%|█████████▌| 191/200 [06:29<00:16, 1.79s/it]\n 96%|█████████▌| 192/200 [06:29<00:10, 1.33s/it]\n 96%|█████████▋| 193/200 [06:29<00:07, 1.01s/it]\n 97%|█████████▋| 194/200 [06:30<00:04, 1.26it/s]\n 98%|█████████▊| 195/200 [06:30<00:03, 1.57it/s]\n 98%|█████████▊| 196/200 [06:33<00:05, 1.49s/it]\n 98%|█████████▊| 197/200 [06:34<00:03, 1.13s/it]\n 99%|█████████▉| 198/200 [06:34<00:01, 1.14it/s]\n100%|█████████▉| 199/200 [06:37<00:01, 1.69s/it]\n100%|██████████| 200/200 [06:38<00:00, 1.27s/it]\n100%|██████████| 200/200 [06:38<00:00, 1.99s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1750704936/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_1750704936/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_1750704936/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_1750704936/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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (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 : 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 : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 398.20353507995605\nerrors 91\nmean length: 1.635\n\nthroughput (request / second): 0.5022557119183827\nthroughput (character / second): 0.8211880889865557\naverage request duration (s) 1.990909526348114\n50%ile request duration (s) 3.3835110664367676\n75%ile request duration (s) 3.4593613743782043\n90%ile request duration (s) 3.5322330474853514\n95%ile request duration (s) 3.5792040824890137\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-llama8b-retune7-90738-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-90738-v1-profiler
Service chaiml-llama8b-retune7-90738-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.36s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama8b-retune7-90738-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.76s
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-llama8b-retune7-90738-v1-profiler
Waiting for inference service chaiml-llama8b-retune7-90738-v1-profiler to be ready
Inference service chaiml-llama8b-retune7-90738-v1-profiler ready after 121.69885873794556s
Pipeline stage MKMLProfilerDeployer completed in 122.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6:/code/chaiverse_profiler_1750705542 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750705542 && 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_1750705542/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6:/code/chaiverse_profiler_1750705979 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750705979 && 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_1750705979/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6:/code/chaiverse_profiler_1750706406 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama8b-retunbbdfcb0628e8f917853bf0afe183c985-deplok8tl6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1750706406 && 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_1750706406/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<11:21, 3.43s/it]\n 1%| | 2/200 [00:03<05:14, 1.59s/it]\n 2%|▏ | 3/200 [00:04<03:15, 1.01it/s]\n 2%|▏ | 4/200 [00:04<02:18, 1.41it/s]\n 2%|▎ | 5/200 [00:07<05:37, 1.73s/it]\n 3%|▎ | 6/200 [00:08<04:00, 1.24s/it]\n 4%|▎ | 7/200 [00:08<02:59, 1.07it/s]\n 4%|▍ | 8/200 [00:11<05:33, 1.74s/it]\n 4%|▍ | 9/200 [00:12<03:55, 1.23s/it]\n 5%|▌ | 10/200 [00:15<06:18, 1.99s/it]\n 6%|▌ | 11/200 [00:19<07:46, 2.47s/it]\n 6%|▌ | 12/200 [00:22<08:42, 2.78s/it]\n 6%|▋ | 13/200 [00:22<06:09, 1.98s/it]\n 7%|▋ | 14/200 [00:23<04:33, 1.47s/it]\n 8%|▊ | 15/200 [00:26<06:26, 2.09s/it]\n 8%|▊ | 16/200 [00:30<07:51, 2.56s/it]\n 8%|▊ | 17/200 [00:33<08:44, 2.87s/it]\n 9%|▉ | 18/200 [00:37<09:17, 3.07s/it]\n 10%|▉ | 19/200 [00:37<06:35, 2.18s/it]\n 10%|█ | 20/200 [00:37<04:49, 1.61s/it]\n 10%|█ | 21/200 [00:38<03:36, 1.21s/it]\n 11%|█ | 22/200 [00:38<02:45, 1.08it/s]\n 12%|█▏ | 23/200 [00:41<05:02, 1.71s/it]\n 12%|█▏ | 24/200 [00:42<03:45, 1.28s/it]\n 12%|█▎ | 25/200 [00:42<02:51, 1.02it/s]\n 13%|█▎ | 26/200 [00:45<05:02, 1.74s/it]\n 14%|█▎ | 27/200 [00:49<06:38, 2.30s/it]\n 14%|█▍ | 28/200 [00:49<04:52, 1.70s/it]\n 14%|█▍ | 29/200 [00:53<06:20, 2.22s/it]\n 15%|█▌ | 30/200 [00:53<04:31, 1.59s/it]\n 16%|█▌ | 31/200 [00:56<06:05, 2.16s/it]\n 16%|█▌ | 32/200 [00:57<04:26, 1.59s/it]\n 16%|█▋ | 33/200 [00:57<03:19, 1.20s/it]\n 17%|█▋ | 34/200 [00:57<02:33, 1.08it/s]\n 18%|█▊ | 35/200 [01:01<04:40, 1.70s/it]\n 18%|█▊ | 36/200 [01:01<03:29, 1.28s/it]\n 18%|█▊ | 37/200 [01:05<05:14, 1.93s/it]\n 19%|█▉ | 38/200 [01:08<06:28, 2.40s/it]\n 20%|█▉ | 39/200 [01:12<07:23, 2.75s/it]\n 20%|██ | 40/200 [01:12<05:21, 2.01s/it]\n 20%|██ | 41/200 [01:12<03:56, 1.49s/it]\n 21%|██ | 42/200 [01:16<05:23, 2.05s/it]\n 22%|██▏ | 43/200 [01:19<06:31, 2.49s/it]\n 22%|██▏ | 44/200 [01:23<07:16, 2.80s/it]\n 22%|██▎ | 45/200 [01:23<05:16, 2.04s/it]\n 23%|██▎ | 46/200 [01:23<03:52, 1.51s/it]\n 24%|██▎ | 47/200 [01:27<05:22, 2.11s/it]\n 24%|██▍ | 48/200 [01:30<06:24, 2.53s/it]\n 24%|██▍ | 49/200 [01:34<07:06, 2.83s/it]\n 25%|██▌ | 50/200 [01:34<05:09, 2.06s/it]\n 26%|██▌ | 51/200 [01:37<06:12, 2.50s/it]\n 26%|██▌ | 52/200 [01:41<06:56, 2.82s/it]\n 26%|██▋ | 53/200 [01:41<05:02, 2.06s/it]\n 27%|██▋ | 54/200 [01:41<03:35, 1.48s/it]\n 28%|██▊ | 55/200 [01:45<05:01, 2.08s/it]\n 28%|██▊ | 56/200 [01:49<06:06, 2.55s/it]\n 28%|██▊ | 57/200 [01:49<04:20, 1.82s/it]\n 29%|██▉ | 58/200 [01:52<05:29, 2.32s/it]\n 30%|██▉ | 59/200 [01:52<03:59, 1.70s/it]\n 30%|███ | 60/200 [01:53<02:58, 1.28s/it]\n 30%|███ | 61/200 [01:56<04:29, 1.94s/it]\n 31%|███ | 62/200 [02:00<05:33, 2.42s/it]\n 32%|███▏ | 63/200 [02:00<04:03, 1.78s/it]\n 32%|███▏ | 64/200 [02:00<03:00, 1.33s/it]\n 32%|███▎ | 65/200 [02:04<04:26, 1.97s/it]\n 33%|███▎ | 66/200 [02:07<05:33, 2.49s/it]\n 34%|███▎ | 67/200 [02:11<06:13, 2.81s/it]\n 34%|███▍ | 68/200 [02:14<06:38, 3.02s/it]\n 34%|███▍ | 69/200 [02:18<06:53, 3.15s/it]\n 35%|███▌ | 70/200 [02:18<04:52, 2.25s/it]\n 36%|███▌ | 71/200 [02:22<05:44, 2.67s/it]\n 36%|███▌ | 72/200 [02:25<06:14, 2.92s/it]\n 36%|███▋ | 73/200 [02:29<06:25, 3.04s/it]\n 37%|███▋ | 74/200 [02:29<04:38, 2.21s/it]\n 38%|███▊ | 75/200 [02:32<05:23, 2.59s/it]\n 38%|███▊ | 76/200 [02:36<06:00, 2.90s/it]\n 38%|███▊ | 77/200 [02:40<06:21, 3.10s/it]\n 39%|███▉ | 78/200 [02:40<04:29, 2.21s/it]\n 40%|███▉ | 79/200 [02:43<05:18, 2.63s/it]\n 40%|████ | 80/200 [02:47<05:46, 2.88s/it]\n 40%|████ | 81/200 [02:50<06:04, 3.07s/it]\n 41%|████ | 82/200 [02:50<04:17, 2.18s/it]\n 42%|████▏ | 83/200 [02:54<05:08, 2.64s/it]\n 42%|████▏ | 84/200 [02:58<05:34, 2.89s/it]\n 42%|████▎ | 85/200 [03:01<05:52, 3.07s/it]\n 43%|████▎ | 86/200 [03:01<04:09, 2.19s/it]\n 44%|████▎ | 87/200 [03:05<04:54, 2.61s/it]\n 44%|████▍ | 88/200 [03:05<03:28, 1.86s/it]\n 44%|████▍ | 89/200 [03:05<02:33, 1.38s/it]\n 45%|████▌ | 90/200 [03:09<03:41, 2.01s/it]\n 46%|████▌ | 91/200 [03:12<04:28, 2.46s/it]\n 46%|████▌ | 92/200 [03:16<05:02, 2.80s/it]\n 46%|████▋ | 93/200 [03:19<05:26, 3.05s/it]\n 47%|████▋ | 94/200 [03:23<05:35, 3.17s/it]\n 48%|████▊ | 95/200 [03:23<03:56, 2.26s/it]\n 48%|████▊ | 96/200 [03:23<02:53, 1.67s/it]\n 48%|████▊ | 97/200 [03:23<02:08, 1.25s/it]\n 49%|████▉ | 98/200 [03:24<01:37, 1.04it/s]\n 50%|████▉ | 99/200 [03:27<02:52, 1.71s/it]\n 50%|█████ | 100/200 [03:31<03:44, 2.24s/it]\n 50%|█████ | 101/200 [03:34<04:18, 2.61s/it]\n 51%|█████ | 102/200 [03:34<03:06, 1.90s/it]\n 52%|█████▏ | 103/200 [03:38<03:51, 2.39s/it]\n 52%|█████▏ | 104/200 [03:41<04:19, 2.71s/it]\n 52%|█████▎ | 105/200 [03:45<04:39, 2.94s/it]\n 53%|█████▎ | 106/200 [03:45<03:21, 2.14s/it]\n 54%|█████▎ | 107/200 [03:49<03:55, 2.53s/it]\n 54%|█████▍ | 108/200 [03:49<02:50, 1.86s/it]\n 55%|█████▍ | 109/200 [03:49<02:06, 1.39s/it]\n 55%|█████▌ | 110/200 [03:53<03:01, 2.01s/it]\n 56%|█████▌ | 111/200 [03:56<03:37, 2.45s/it]\n 56%|█████▌ | 112/200 [03:56<02:38, 1.80s/it]\n 56%|█████▋ | 113/200 [03:57<01:52, 1.30s/it]\n 57%|█████▋ | 114/200 [04:00<02:53, 2.01s/it]\n 57%|█████▊ | 115/200 [04:04<03:25, 2.42s/it]\n 58%|█████▊ | 116/200 [04:07<03:49, 2.73s/it]\n 58%|█████▊ | 117/200 [04:11<04:05, 2.95s/it]\n 59%|█████▉ | 118/200 [04:14<04:14, 3.10s/it]\n 60%|█████▉ | 119/200 [04:17<04:20, 3.22s/it]\n 60%|██████ | 120/200 [04:21<04:25, 3.32s/it]\n 60%|██████ | 121/200 [04:24<04:25, 3.36s/it]\n 61%|██████ | 122/200 [04:28<04:25, 3.41s/it]\n 62%|██████▏ | 123/200 [04:32<04:25, 3.45s/it]\n 62%|██████▏ | 124/200 [04:35<04:18, 3.40s/it]\n 62%|██████▎ | 125/200 [04:35<03:03, 2.45s/it]\n 63%|██████▎ | 126/200 [04:39<03:27, 2.80s/it]\n 64%|██████▎ | 127/200 [04:39<02:25, 2.00s/it]\n 64%|██████▍ | 128/200 [04:39<01:46, 1.48s/it]\n 64%|██████▍ | 129/200 [04:43<02:27, 2.07s/it]\n 65%|██████▌ | 130/200 [04:46<02:54, 2.49s/it]\n 66%|██████▌ | 131/200 [04:46<02:05, 1.82s/it]\n 66%|██████▌ | 132/200 [04:46<01:31, 1.35s/it]\n 66%|██████▋ | 133/200 [04:50<02:12, 1.98s/it]\n 67%|██████▋ | 134/200 [04:54<02:43, 2.48s/it]\n 68%|██████▊ | 135/200 [04:54<01:55, 1.77s/it]\n 68%|██████▊ | 136/200 [04:54<01:24, 1.32s/it]\n 68%|██████▊ | 137/200 [04:54<01:03, 1.01s/it]\n 69%|██████▉ | 138/200 [04:58<01:49, 1.77s/it]\n 70%|██████▉ | 139/200 [05:01<02:19, 2.28s/it]\n 70%|███████ | 140/200 [05:05<02:40, 2.67s/it]\n 70%|███████ | 141/200 [05:08<02:51, 2.91s/it]\n 71%|███████ | 142/200 [05:09<02:02, 2.12s/it]\n 72%|███████▏ | 143/200 [05:12<02:24, 2.53s/it]\n 72%|███████▏ | 144/200 [05:16<02:37, 2.82s/it]\n 72%|███████▎ | 145/200 [05:19<02:45, 3.01s/it]\n 73%|███████▎ | 146/200 [05:19<01:58, 2.19s/it]\n 74%|███████▎ | 147/200 [05:20<01:25, 1.61s/it]\n 74%|███████▍ | 148/200 [05:23<01:52, 2.17s/it]\n 74%|███████▍ | 149/200 [05:27<02:10, 2.56s/it]\n 75%|███████▌ | 150/200 [05:27<01:34, 1.89s/it]\n 76%|███████▌ | 151/200 [05:27<01:08, 1.40s/it]\n 76%|███████▌ | 152/200 [05:27<00:51, 1.06s/it]\n 76%|███████▋ | 153/200 [05:28<00:38, 1.21it/s]\n 77%|███████▋ | 154/200 [05:28<00:28, 1.62it/s]\n 78%|███████▊ | 155/200 [05:28<00:23, 1.92it/s]\n 78%|███████▊ | 156/200 [05:32<01:02, 1.43s/it]\n 78%|███████▊ | 157/200 [05:35<01:28, 2.05s/it]\n 79%|███████▉ | 158/200 [05:35<01:03, 1.51s/it]\n 80%|███████▉ | 159/200 [05:39<01:28, 2.17s/it]\n 80%|████████ | 160/200 [05:43<01:42, 2.55s/it]\n 80%|████████ | 161/200 [05:46<01:51, 2.85s/it]\n 81%|████████ | 162/200 [05:46<01:17, 2.03s/it]\n 82%|████████▏ | 163/200 [05:46<00:55, 1.50s/it]\n 82%|████████▏ | 164/200 [05:47<00:40, 1.14s/it]\n 82%|████████▎ | 165/200 [05:47<00:30, 1.14it/s]\n 83%|████████▎ | 166/200 [05:50<00:56, 1.66s/it]\n 84%|████████▎ | 167/200 [05:54<01:12, 2.21s/it]\n 84%|████████▍ | 168/200 [05:57<01:22, 2.59s/it]\n 84%|████████▍ | 169/200 [05:58<00:58, 1.89s/it]\n 85%|████████▌ | 170/200 [06:01<01:11, 2.37s/it]\n 86%|████████▌ | 171/200 [06:01<00:50, 1.74s/it]\n 86%|████████▌ | 172/200 [06:02<00:36, 1.30s/it]\n 86%|████████▋ | 173/200 [06:02<00:25, 1.05it/s]\n 87%|████████▋ | 174/200 [06:06<00:45, 1.75s/it]\n 88%|████████▊ | 175/200 [06:09<00:56, 2.27s/it]\n 88%|████████▊ | 176/200 [06:13<01:03, 2.64s/it]\n 88%|████████▊ | 177/200 [06:13<00:43, 1.89s/it]\n 89%|████████▉ | 178/200 [06:16<00:52, 2.38s/it]\n 90%|████████▉ | 179/200 [06:20<00:56, 2.71s/it]\n 90%|█████████ | 180/200 [06:20<00:38, 1.93s/it]\n 90%|█████████ | 181/200 [06:23<00:45, 2.40s/it]\n 91%|█████████ | 182/200 [06:24<00:31, 1.76s/it]\n 92%|█████████▏| 183/200 [06:24<00:22, 1.31s/it]\n 92%|█████████▏| 184/200 [06:27<00:31, 1.98s/it]\n 92%|█████████▎| 185/200 [06:31<00:36, 2.42s/it]\n 93%|█████████▎| 186/200 [06:31<00:24, 1.77s/it]\n 94%|█████████▎| 187/200 [06:31<00:17, 1.32s/it]\n 94%|█████████▍| 188/200 [06:32<00:12, 1.00s/it]\n 94%|█████████▍| 189/200 [06:32<00:08, 1.27it/s]\n 95%|█████████▌| 190/200 [06:32<00:06, 1.57it/s]\n 96%|█████████▌| 191/200 [06:36<00:13, 1.50s/it]\n 96%|█████████▌| 192/200 [06:39<00:16, 2.09s/it]\n 96%|█████████▋| 193/200 [06:43<00:17, 2.52s/it]\n 97%|█████████▋| 194/200 [06:43<00:11, 1.84s/it]\n 98%|█████████▊| 195/200 [06:46<00:11, 2.33s/it]\n 98%|█████████▊| 196/200 [06:50<00:10, 2.67s/it]\n 98%|█████████▊| 197/200 [06:53<00:08, 2.91s/it]\n 99%|█████████▉| 198/200 [06:54<00:04, 2.12s/it]\n100%|█████████▉| 199/200 [06:54<00:01, 1.57s/it]\n100%|██████████| 200/200 [06:54<00:00, 1.19s/it]\n100%|██████████| 200/200 [06:54<00:00, 2.07s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1750706406/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_1750706406/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_1750706406/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_1750706406/profiles.py", line 277, in run_batch_profile\n analysis_data.write_jsonlines([batch_profile.to_dict()], path)\n File "/code/inference_analysis/data.py", line 64, in write_jsonlines\n f.write(json.dumps(row) + \'\\n\')\n File "/opt/conda/lib/python3.10/json/__init__.py", line 231, in dumps\n return _default_encoder.encode(obj)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 199, in encode\n chunks = self.iterencode(o, _one_shot=True)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 257, in iterencode\n return _iterencode(o, 0)\n File "/opt/conda/lib/python3.10/json/encoder.py", line 179, in default\n raise TypeError(f\'Object of type {o.__class__.__name__} \'\nTypeError: Object of type ResponseStats is not JSON serializable\ncommand terminated with exit code 1\n, output: waiting for startup of endpoint=\'localhost\' route=\'GPT-J-6B-lit-v2\' namespace=\'tenant-chaiml-guanaco\' reward=False url_format=\'{endpoint}.{namespace}.k.chaiverse.com\'\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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): 414.65822982788086\nerrors 88\nmean length: 1.68\n\nthroughput (request / second): 0.4823249259589454\nthroughput (character / second): 0.8103058756110283\naverage request duration (s) 2.073180671930313\n50%ile request duration (s) 3.4535290002822876\n75%ile request duration (s) 3.503623127937317\n90%ile request duration (s) 3.577239227294922\n95%ile request duration (s) 3.631424939632416\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-llama8b-retune7-90738-v1-profiler is running
Tearing down inference service chaiml-llama8b-retune7-90738-v1-profiler
Service chaiml-llama8b-retune7-90738-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.75s
Shutdown handler de-registered
chaiml-llama8b-retune7-_90738_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama8b-retune7-_90738_v1 status is now torndown due to DeploymentManager action