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-llama-8b-nis-800k-9881-v2-mkmlizer
Waiting for job on chaiml-llama-8b-nis-800k-9881-v2-mkmlizer to finish
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ belonging to: ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ║ ║
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: Downloaded to shared memory in 22.784s
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: Checking if ChaiML/llama_8b_nis_800ksamp_512seq_retune_cos_time_bestep_5733 already exists in ChaiML
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpjkgrwtxo, device:0
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: quantized model in 19.723s
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: Processed model ChaiML/llama_8b_nis_800ksamp_512seq_retune_cos_time_bestep_5733 in 42.507s
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia/special_tokens_map.json
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia/config.json
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia/tokenizer_config.json
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia/tokenizer.json
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-nis-800k-9881-v2/nvidia/flywheel_model.0.safetensors
chaiml-llama-8b-nis-800k-9881-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:07, 38.93it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:04, 58.38it/s]
Loading 0: 7%|▋ | 19/291 [00:00<00:05, 48.06it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:05, 48.54it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:05, 50.88it/s]
Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 44.19it/s]
Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 43.31it/s]
Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 48.78it/s]
Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 43.76it/s]
Loading 0: 21%|██ | 60/291 [00:01<00:05, 42.95it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 48.26it/s]
Loading 0: 25%|██▍ | 72/291 [00:01<00:04, 48.69it/s]
Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 40.25it/s]
Loading 0: 29%|██▊ | 83/291 [00:02<00:06, 30.46it/s]
Loading 0: 30%|██▉ | 87/291 [00:02<00:07, 28.69it/s]
Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 33.23it/s]
Loading 0: 33%|███▎ | 97/291 [00:02<00:05, 33.83it/s]
Loading 0: 35%|███▌ | 102/291 [00:02<00:05, 37.29it/s]
Loading 0: 37%|███▋ | 107/291 [00:02<00:04, 38.97it/s]
Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 39.26it/s]
Loading 0: 40%|████ | 117/291 [00:02<00:04, 41.39it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 35.16it/s]
Loading 0: 44%|████▍ | 129/291 [00:03<00:03, 42.52it/s]
Loading 0: 46%|████▌ | 134/291 [00:03<00:03, 43.03it/s]
Loading 0: 48%|████▊ | 139/291 [00:03<00:03, 44.03it/s]
Loading 0: 49%|████▉ | 144/291 [00:03<00:03, 45.55it/s]
Loading 0: 51%|█████ | 149/291 [00:03<00:03, 35.51it/s]
Loading 0: 54%|█████▍ | 157/291 [00:03<00:03, 44.16it/s]
Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 45.43it/s]
Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 37.74it/s]
Loading 0: 59%|█████▉ | 173/291 [00:04<00:02, 42.30it/s]
Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 46.22it/s]
Loading 0: 64%|██████▎ | 185/291 [00:04<00:02, 45.75it/s]
Loading 0: 65%|██████▌ | 190/291 [00:04<00:03, 27.99it/s]
Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 29.20it/s]
Loading 0: 69%|██████▉ | 202/291 [00:05<00:02, 38.00it/s]
Loading 0: 71%|███████ | 207/291 [00:05<00:02, 40.29it/s]
Loading 0: 73%|███████▎ | 212/291 [00:05<00:02, 35.03it/s]
Loading 0: 75%|███████▌ | 219/291 [00:05<00:01, 42.41it/s]
Loading 0: 77%|███████▋ | 224/291 [00:05<00:01, 42.61it/s]
Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 42.30it/s]
Loading 0: 81%|████████ | 235/291 [00:05<00:01, 40.92it/s]
Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 41.63it/s]
Loading 0: 85%|████████▍ | 247/291 [00:06<00:00, 47.12it/s]
Loading 0: 87%|████████▋ | 252/291 [00:06<00:00, 47.54it/s]
Loading 0: 88%|████████▊ | 257/291 [00:06<00:00, 38.18it/s]
Loading 0: 91%|█████████ | 264/291 [00:06<00:00, 45.44it/s]
Loading 0: 93%|█████████▎| 270/291 [00:06<00:00, 46.86it/s]
Loading 0: 95%|█████████▍| 276/291 [00:06<00:00, 39.98it/s]
Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 41.73it/s]
Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 36.92it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00, 32.15it/s]
Job chaiml-llama-8b-nis-800k-9881-v2-mkmlizer completed after 64.96s with status: succeeded
Stopping job with name chaiml-llama-8b-nis-800k-9881-v2-mkmlizer
Pipeline stage MKMLizer completed in 65.43s
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-llama-8b-nis-800k-9881-v2
Waiting for inference service chaiml-llama-8b-nis-800k-9881-v2 to be ready
Inference service chaiml-llama-8b-nis-800k-9881-v2 ready after 200.71587467193604s
Pipeline stage MKMLDeployer completed in 201.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1787118911743164s
Received healthy response to inference request in 2.806842565536499s
Received healthy response to inference request in 3.397310972213745s
Received healthy response to inference request in 4.866060018539429s
Received healthy response to inference request in 3.112891674041748s
5 requests
0 failed requests
5th percentile: 2.8680523872375487
10th percentile: 2.9292622089385985
20th percentile: 3.0516818523406983
30th percentile: 3.1260557174682617
40th percentile: 3.152383804321289
50th percentile: 3.1787118911743164
60th percentile: 3.266151523590088
70th percentile: 3.3535911560058596
80th percentile: 3.6910607814788823
90th percentile: 4.278560400009155
95th percentile: 4.572310209274292
99th percentile: 4.8073100566864015
mean time: 3.4723634243011476
Pipeline stage StressChecker completed in 19.00s
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 0.65s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.89s
Shutdown handler de-registered
chaiml-llama-8b-nis-800k_9881_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...
%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-llama-8b-nis-800k-9881-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.44s
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-llama-8b-nis-800k-9881-v2-profiler
Waiting for inference service chaiml-llama-8b-nis-800k-9881-v2-profiler to be ready
Inference service chaiml-llama-8b-nis-800k-9881-v2-profiler ready after 201.88133025169373s
Pipeline stage MKMLProfilerDeployer completed in 202.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8:/code/chaiverse_profiler_1751863252 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751863252 && 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_1751863252/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8:/code/chaiverse_profiler_1751863692 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751863692 && 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_1751863692/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8:/code/chaiverse_profiler_1751864117 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplojctv8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751864117 && 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_1751864117/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<11:13, 3.38s/it]\n 1%| | 2/200 [00:06<11:17, 3.42s/it]\n 2%|▏ | 3/200 [00:10<11:07, 3.39s/it]\n 2%|▏ | 4/200 [00:13<11:07, 3.41s/it]\n 2%|▎ | 5/200 [00:17<11:04, 3.41s/it]\n 3%|▎ | 6/200 [00:17<07:24, 2.29s/it]\n 4%|▎ | 7/200 [00:20<08:30, 2.64s/it]\n 4%|▍ | 8/200 [00:24<09:20, 2.92s/it]\n 4%|▍ | 9/200 [00:24<06:30, 2.05s/it]\n 5%|▌ | 10/200 [00:24<04:43, 1.49s/it]\n 6%|▌ | 11/200 [00:24<03:30, 1.11s/it]\n 6%|▌ | 12/200 [00:24<02:39, 1.18it/s]\n 6%|▋ | 13/200 [00:28<05:04, 1.63s/it]\n 7%|▋ | 14/200 [00:28<03:44, 1.21s/it]\n 8%|▊ | 15/200 [00:32<05:48, 1.88s/it]\n 8%|▊ | 16/200 [00:32<04:15, 1.39s/it]\n 8%|▊ | 17/200 [00:32<03:13, 1.06s/it]\n 9%|▉ | 18/200 [00:35<05:23, 1.78s/it]\n 10%|▉ | 19/200 [00:36<03:57, 1.31s/it]\n 10%|█ | 20/200 [00:39<05:50, 1.95s/it]\n 10%|█ | 21/200 [00:43<07:10, 2.41s/it]\n 11%|█ | 22/200 [00:43<05:12, 1.76s/it]\n 12%|█▏ | 23/200 [00:46<06:37, 2.25s/it]\n 12%|█▏ | 24/200 [00:50<07:37, 2.60s/it]\n 12%|█▎ | 25/200 [00:53<08:19, 2.85s/it]\n 13%|█▎ | 26/200 [00:57<08:44, 3.01s/it]\n 14%|█▎ | 27/200 [00:57<06:11, 2.15s/it]\n 14%|█▍ | 28/200 [01:00<07:17, 2.54s/it]\n 14%|█▍ | 29/200 [01:04<08:18, 2.92s/it]\n 15%|█▌ | 30/200 [01:04<05:53, 2.08s/it]\n 16%|█▌ | 31/200 [01:07<06:56, 2.46s/it]\n 16%|█▌ | 32/200 [01:08<05:01, 1.79s/it]\n 16%|█▋ | 33/200 [01:08<03:42, 1.33s/it]\n 17%|█▋ | 34/200 [01:08<02:47, 1.01s/it]\n 18%|█▊ | 35/200 [01:12<04:48, 1.75s/it]\n 18%|█▊ | 36/200 [01:12<03:31, 1.29s/it]\n 18%|█▊ | 37/200 [01:12<02:40, 1.02it/s]\n 19%|█▉ | 38/200 [01:15<04:36, 1.71s/it]\n 20%|█▉ | 39/200 [01:19<05:59, 2.23s/it]\n 20%|██ | 40/200 [01:19<04:20, 1.63s/it]\n 20%|██ | 41/200 [01:23<05:42, 2.15s/it]\n 21%|██ | 42/200 [01:23<04:09, 1.58s/it]\n 22%|██▏ | 43/200 [01:26<05:33, 2.12s/it]\n 22%|██▏ | 44/200 [01:30<06:31, 2.51s/it]\n 22%|██▎ | 45/200 [01:33<07:15, 2.81s/it]\n 23%|██▎ | 46/200 [01:36<07:38, 2.98s/it]\n 24%|██▎ | 47/200 [01:37<05:29, 2.16s/it]\n 24%|██▍ | 48/200 [01:40<06:25, 2.53s/it]\n 24%|██▍ | 49/200 [01:40<04:37, 1.84s/it]\n 25%|██▌ | 50/200 [01:44<05:53, 2.35s/it]\n 26%|██▌ | 51/200 [01:47<06:37, 2.67s/it]\n 26%|██▌ | 52/200 [01:47<04:41, 1.91s/it]\n 26%|██▋ | 53/200 [01:51<05:47, 2.36s/it]\n 27%|██▋ | 54/200 [01:54<06:31, 2.68s/it]\n 28%|██▊ | 55/200 [01:58<06:57, 2.88s/it]\n 28%|██▊ | 56/200 [01:58<04:55, 2.05s/it]\n 28%|██▊ | 57/200 [02:01<05:55, 2.49s/it]\n 29%|██▉ | 58/200 [02:05<06:30, 2.75s/it]\n 30%|██▉ | 59/200 [02:05<04:36, 1.96s/it]\n 30%|███ | 60/200 [02:08<05:34, 2.39s/it]\n 30%|███ | 61/200 [02:12<06:19, 2.73s/it]\n 31%|███ | 62/200 [02:15<06:44, 2.93s/it]\n 32%|███▏ | 63/200 [02:18<07:00, 3.07s/it]\n 32%|███▏ | 64/200 [02:19<04:57, 2.19s/it]\n 32%|███▎ | 65/200 [02:22<05:47, 2.58s/it]\n 33%|███▎ | 66/200 [02:25<06:19, 2.83s/it]\n 34%|███▎ | 67/200 [02:26<04:28, 2.02s/it]\n 34%|███▍ | 68/200 [02:26<03:16, 1.49s/it]\n 34%|███▍ | 69/200 [02:26<02:26, 1.11s/it]\n 35%|███▌ | 70/200 [02:29<03:54, 1.80s/it]\n 36%|███▌ | 71/200 [02:30<02:51, 1.33s/it]\n 36%|███▌ | 72/200 [02:30<02:08, 1.00s/it]\n 36%|███▋ | 73/200 [02:33<03:36, 1.70s/it]\n 37%|███▋ | 74/200 [02:37<04:35, 2.19s/it]\n 38%|███▊ | 75/200 [02:40<05:19, 2.56s/it]\n 38%|███▊ | 76/200 [02:40<03:50, 1.86s/it]\n 38%|███▊ | 77/200 [02:44<04:49, 2.36s/it]\n 39%|███▉ | 78/200 [02:47<05:28, 2.69s/it]\n 40%|███▉ | 79/200 [02:51<05:51, 2.90s/it]\n 40%|████ | 80/200 [02:54<06:07, 3.06s/it]\n 40%|████ | 81/200 [02:54<04:23, 2.22s/it]\n 41%|████ | 82/200 [02:58<05:05, 2.59s/it]\n 42%|████▏ | 83/200 [03:01<05:31, 2.83s/it]\n 42%|████▏ | 84/200 [03:05<05:53, 3.04s/it]\n 42%|████▎ | 85/200 [03:05<04:09, 2.17s/it]\n 43%|████▎ | 86/200 [03:05<03:01, 1.60s/it]\n 44%|████▎ | 87/200 [03:09<04:02, 2.14s/it]\n 44%|████▍ | 88/200 [03:12<04:43, 2.53s/it]\n 44%|████▍ | 89/200 [03:16<05:15, 2.84s/it]\n 45%|████▌ | 90/200 [03:16<03:43, 2.03s/it]\n 46%|████▌ | 91/200 [03:19<04:24, 2.43s/it]\n 46%|████▌ | 92/200 [03:23<04:57, 2.75s/it]\n 46%|████▋ | 93/200 [03:26<05:20, 2.99s/it]\n 47%|████▋ | 94/200 [03:29<05:29, 3.11s/it]\n 48%|████▊ | 95/200 [03:30<03:52, 2.22s/it]\n 48%|████▊ | 96/200 [03:33<04:27, 2.57s/it]\n 48%|████▊ | 97/200 [03:37<04:58, 2.90s/it]\n 49%|████▉ | 98/200 [03:40<05:12, 3.06s/it]\n 50%|████▉ | 99/200 [03:40<03:40, 2.18s/it]\n 50%|█████ | 100/200 [03:44<04:17, 2.57s/it]\n 50%|█████ | 101/200 [03:47<04:42, 2.86s/it]\n 51%|█████ | 102/200 [03:51<04:56, 3.02s/it]\n 52%|█████▏ | 103/200 [03:54<05:04, 3.14s/it]\n 52%|█████▏ | 104/200 [03:57<05:09, 3.22s/it]\n 52%|█████▎ | 105/200 [04:01<05:11, 3.27s/it]\n 53%|█████▎ | 106/200 [04:01<03:38, 2.33s/it]\n 54%|█████▎ | 107/200 [04:04<04:07, 2.66s/it]\n 54%|█████▍ | 108/200 [04:08<04:29, 2.93s/it]\n 55%|█████▍ | 109/200 [04:08<03:09, 2.08s/it]\n 55%|█████▌ | 110/200 [04:08<02:17, 1.53s/it]\n 56%|█████▌ | 111/200 [04:09<01:42, 1.15s/it]\n 56%|█████▌ | 112/200 [04:09<01:17, 1.14it/s]\n 56%|█████▋ | 113/200 [04:09<01:00, 1.43it/s]\n 57%|█████▋ | 114/200 [04:13<02:13, 1.55s/it]\n 57%|█████▊ | 115/200 [04:13<01:38, 1.15s/it]\n 58%|█████▊ | 116/200 [04:16<02:33, 1.83s/it]\n 58%|█████▊ | 117/200 [04:20<03:12, 2.32s/it]\n 59%|█████▉ | 118/200 [04:23<03:36, 2.64s/it]\n 60%|█████▉ | 119/200 [04:23<02:35, 1.92s/it]\n 60%|██████ | 120/200 [04:27<03:10, 2.38s/it]\n 60%|██████ | 121/200 [04:30<03:30, 2.66s/it]\n 61%|██████ | 122/200 [04:34<03:45, 2.89s/it]\n 62%|██████▏ | 123/200 [04:34<02:38, 2.06s/it]\n 62%|██████▏ | 124/200 [04:37<03:05, 2.44s/it]\n 62%|██████▎ | 125/200 [04:37<02:13, 1.78s/it]\n 63%|██████▎ | 126/200 [04:41<02:51, 2.32s/it]\n 64%|██████▎ | 127/200 [04:41<02:01, 1.66s/it]\n 64%|██████▍ | 128/200 [04:41<01:28, 1.24s/it]\n 64%|██████▍ | 129/200 [04:45<02:14, 1.90s/it]\n 65%|██████▌ | 130/200 [04:48<02:46, 2.38s/it]\n 66%|██████▌ | 131/200 [04:52<03:05, 2.69s/it]\n 66%|██████▌ | 132/200 [04:55<03:18, 2.93s/it]\n 66%|██████▋ | 133/200 [04:55<02:19, 2.09s/it]\n 67%|██████▋ | 134/200 [04:59<02:47, 2.54s/it]\n 68%|██████▊ | 135/200 [04:59<01:58, 1.82s/it]\n 68%|██████▊ | 136/200 [04:59<01:26, 1.34s/it]\n 68%|██████▊ | 137/200 [05:03<02:08, 2.03s/it]\n 69%|██████▉ | 138/200 [05:06<02:31, 2.44s/it]\n 70%|██████▉ | 139/200 [05:06<01:46, 1.75s/it]\n 70%|███████ | 140/200 [05:07<01:17, 1.30s/it]\n 70%|███████ | 141/200 [05:10<01:54, 1.94s/it]\n 71%|███████ | 142/200 [05:10<01:22, 1.43s/it]\n 72%|███████▏ | 143/200 [05:10<01:01, 1.07s/it]\n 72%|███████▏ | 144/200 [05:14<01:40, 1.79s/it]\n 72%|███████▎ | 145/200 [05:17<02:06, 2.30s/it]\n 73%|███████▎ | 146/200 [05:18<01:30, 1.68s/it]\n 74%|███████▎ | 147/200 [05:21<01:57, 2.22s/it]\n 74%|███████▍ | 148/200 [05:21<01:24, 1.62s/it]\n 74%|███████▍ | 149/200 [05:25<01:50, 2.16s/it]\n 75%|███████▌ | 150/200 [05:25<01:18, 1.58s/it]\n 76%|███████▌ | 151/200 [05:29<01:45, 2.15s/it]\n 76%|███████▌ | 152/200 [05:32<02:00, 2.52s/it]\n 76%|███████▋ | 153/200 [05:32<01:26, 1.83s/it]\n 77%|███████▋ | 154/200 [05:36<01:46, 2.32s/it]\n 78%|███████▊ | 155/200 [05:36<01:16, 1.70s/it]\n 78%|███████▊ | 156/200 [05:39<01:38, 2.23s/it]\n 78%|███████▊ | 157/200 [05:43<01:50, 2.57s/it]\n 79%|███████▉ | 158/200 [05:46<01:57, 2.81s/it]\n 80%|███████▉ | 159/200 [05:50<02:03, 3.02s/it]\n 80%|████████ | 160/200 [05:53<02:05, 3.15s/it]\n 80%|████████ | 161/200 [05:57<02:07, 3.26s/it]\n 81%|████████ | 162/200 [06:00<02:06, 3.34s/it]\n 82%|████████▏ | 163/200 [06:03<02:03, 3.35s/it]\n 82%|████████▏ | 164/200 [06:07<02:01, 3.39s/it]\n 82%|████████▎ | 165/200 [06:10<01:57, 3.37s/it]\n 83%|████████▎ | 166/200 [06:10<01:21, 2.39s/it]\n 84%|████████▎ | 167/200 [06:11<00:57, 1.75s/it]\n 84%|████████▍ | 168/200 [06:11<00:41, 1.30s/it]\n 84%|████████▍ | 169/200 [06:11<00:30, 1.01it/s]\n 85%|████████▌ | 170/200 [06:15<00:52, 1.74s/it]\n 86%|████████▌ | 171/200 [06:18<01:05, 2.25s/it]\n 86%|████████▌ | 172/200 [06:18<00:46, 1.65s/it]\n 86%|████████▋ | 173/200 [06:22<01:00, 2.23s/it]\n 87%|████████▋ | 174/200 [06:25<01:06, 2.55s/it]\n 88%|████████▊ | 175/200 [06:25<00:46, 1.86s/it]\n 88%|████████▊ | 176/200 [06:26<00:33, 1.38s/it]\n 88%|████████▊ | 177/200 [06:26<00:23, 1.04s/it]\n 89%|████████▉ | 178/200 [06:29<00:38, 1.75s/it]\n 90%|████████▉ | 179/200 [06:30<00:27, 1.30s/it]\n 90%|█████████ | 180/200 [06:33<00:38, 1.95s/it]\n 90%|█████████ | 181/200 [06:33<00:27, 1.43s/it]\n 91%|█████████ | 182/200 [06:37<00:36, 2.04s/it]\n 92%|█████████▏| 183/200 [06:37<00:24, 1.47s/it]\n 92%|█████████▏| 184/200 [06:40<00:33, 2.07s/it]\n 92%|█████████▎| 185/200 [06:44<00:37, 2.51s/it]\n 93%|█████████▎| 186/200 [06:44<00:25, 1.79s/it]\n 94%|█████████▎| 187/200 [06:47<00:29, 2.28s/it]\n 94%|█████████▍| 188/200 [06:51<00:31, 2.66s/it]\n 94%|█████████▍| 189/200 [06:51<00:20, 1.90s/it]\n 95%|█████████▌| 190/200 [06:55<00:23, 2.38s/it]\n 96%|█████████▌| 191/200 [06:58<00:24, 2.72s/it]\n 96%|█████████▌| 192/200 [06:58<00:15, 1.94s/it]\n 96%|█████████▋| 193/200 [07:02<00:17, 2.46s/it]\n 97%|█████████▋| 194/200 [07:02<00:10, 1.76s/it]\n 98%|█████████▊| 195/200 [07:05<00:11, 2.26s/it]\n 98%|█████████▊| 196/200 [07:09<00:10, 2.61s/it]\n 98%|█████████▊| 197/200 [07:12<00:08, 2.83s/it]\n 99%|█████████▉| 198/200 [07:12<00:04, 2.02s/it]\n100%|█████████▉| 199/200 [07:16<00:02, 2.45s/it]\n100%|██████████| 200/200 [07:16<00:00, 1.78s/it]\n100%|██████████| 200/200 [07:16<00:00, 2.18s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1751864117/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_1751864117/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_1751864117/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_1751864117/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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (0,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 436.48937034606934\nerrors 78\nmean length: 1.83\n\nthroughput (request / second): 0.45820130703625284\nthroughput (character / second): 0.8385083918763427\naverage request duration (s) 2.182341959476471\n50%ile request duration (s) 3.3875926733016968\n75%ile request duration (s) 3.4519266486167908\n90%ile request duration (s) 3.514340305328369\n95%ile request duration (s) 3.5437506318092344\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-llama-8b-nis-800k-9881-v2-profiler is running
Tearing down inference service chaiml-llama-8b-nis-800k-9881-v2-profiler
Service chaiml-llama-8b-nis-800k-9881-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.20s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-nis-800k-9881-v2-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 3.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-nis-800k-9881-v2-profiler
Waiting for inference service chaiml-llama-8b-nis-800k-9881-v2-profiler to be ready
Inference service chaiml-llama-8b-nis-800k-9881-v2-profiler ready after 40.507720947265625s
Pipeline stage MKMLProfilerDeployer completed in 41.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn:/code/chaiverse_profiler_1751864669 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751864669 && 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_1751864669/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn:/code/chaiverse_profiler_1751865054 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751865054 && 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_1751865054/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn:/code/chaiverse_profiler_1751865433 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-nis-7aaedea26b9a0c0f4d7ba7809d80c009-deplordltn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1751865433 && 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_1751865433/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<10:48, 3.26s/it]\n 1%| | 2/200 [00:03<04:52, 1.48s/it]\n 2%|▏ | 3/200 [00:06<07:37, 2.32s/it]\n 2%|▏ | 4/200 [00:10<08:52, 2.72s/it]\n 2%|▎ | 5/200 [00:13<09:31, 2.93s/it]\n 3%|▎ | 6/200 [00:13<06:30, 2.01s/it]\n 4%|▎ | 7/200 [00:13<04:37, 1.44s/it]\n 4%|▍ | 8/200 [00:17<06:30, 2.03s/it]\n 4%|▍ | 9/200 [00:20<07:45, 2.44s/it]\n 5%|▌ | 10/200 [00:20<05:34, 1.76s/it]\n 6%|▌ | 11/200 [00:24<07:02, 2.24s/it]\n 6%|▌ | 12/200 [00:27<08:01, 2.56s/it]\n 6%|▋ | 13/200 [00:27<05:47, 1.86s/it]\n 7%|▋ | 14/200 [00:30<07:08, 2.30s/it]\n 8%|▊ | 15/200 [00:31<05:04, 1.64s/it]\n 8%|▊ | 16/200 [00:34<06:35, 2.15s/it]\n 8%|▊ | 17/200 [00:37<07:42, 2.53s/it]\n 9%|▉ | 18/200 [00:41<08:24, 2.77s/it]\n 10%|▉ | 19/200 [00:44<08:54, 2.95s/it]\n 10%|█ | 20/200 [00:44<06:18, 2.10s/it]\n 10%|█ | 21/200 [00:44<04:36, 1.55s/it]\n 11%|█ | 22/200 [00:45<03:25, 1.16s/it]\n 12%|█▏ | 23/200 [00:45<02:37, 1.13it/s]\n 12%|█▏ | 24/200 [00:48<04:44, 1.62s/it]\n 12%|█▎ | 25/200 [00:52<06:11, 2.12s/it]\n 13%|█▎ | 26/200 [00:55<07:11, 2.48s/it]\n 14%|█▎ | 27/200 [00:58<07:55, 2.75s/it]\n 14%|█▍ | 28/200 [01:02<08:20, 2.91s/it]\n 14%|█▍ | 29/200 [01:02<06:00, 2.11s/it]\n 15%|█▌ | 30/200 [01:02<04:24, 1.55s/it]\n 16%|█▌ | 31/200 [01:05<05:53, 2.09s/it]\n 16%|█▌ | 32/200 [01:09<06:55, 2.47s/it]\n 16%|█▋ | 33/200 [01:12<07:36, 2.73s/it]\n 17%|█▋ | 34/200 [01:12<05:29, 1.98s/it]\n 18%|█▊ | 35/200 [01:16<06:35, 2.39s/it]\n 18%|█▊ | 36/200 [01:16<04:46, 1.75s/it]\n 18%|█▊ | 37/200 [01:16<03:32, 1.31s/it]\n 19%|█▉ | 38/200 [01:20<05:09, 1.91s/it]\n 20%|█▉ | 39/200 [01:20<03:41, 1.37s/it]\n 20%|██ | 40/200 [01:23<05:19, 2.00s/it]\n 20%|██ | 41/200 [01:26<06:20, 2.40s/it]\n 21%|██ | 42/200 [01:30<07:02, 2.67s/it]\n 22%|██▏ | 43/200 [01:30<04:59, 1.91s/it]\n 22%|██▏ | 44/200 [01:33<06:09, 2.37s/it]\n 22%|██▎ | 45/200 [01:37<06:51, 2.65s/it]\n 23%|██▎ | 46/200 [01:40<07:19, 2.85s/it]\n 24%|██▎ | 47/200 [01:40<05:11, 2.03s/it]\n 24%|██▍ | 48/200 [01:40<03:47, 1.50s/it]\n 24%|██▍ | 49/200 [01:41<02:49, 1.12s/it]\n 25%|██▌ | 50/200 [01:44<04:27, 1.78s/it]\n 26%|██▌ | 51/200 [01:44<03:16, 1.32s/it]\n 26%|██▌ | 52/200 [01:47<04:44, 1.92s/it]\n 26%|██▋ | 53/200 [01:51<05:50, 2.39s/it]\n 27%|██▋ | 54/200 [01:54<06:28, 2.66s/it]\n 28%|██▊ | 55/200 [01:58<06:54, 2.86s/it]\n 28%|██▊ | 56/200 [02:01<07:11, 3.00s/it]\n 28%|██▊ | 57/200 [02:04<07:22, 3.10s/it]\n 29%|██▉ | 58/200 [02:07<07:24, 3.13s/it]\n 30%|██▉ | 59/200 [02:08<05:18, 2.26s/it]\n 30%|███ | 60/200 [02:11<06:05, 2.61s/it]\n 30%|███ | 61/200 [02:14<06:33, 2.83s/it]\n 31%|███ | 62/200 [02:15<04:38, 2.02s/it]\n 32%|███▏ | 63/200 [02:15<03:23, 1.48s/it]\n 32%|███▏ | 64/200 [02:15<02:30, 1.11s/it]\n 32%|███▎ | 65/200 [02:15<01:54, 1.18it/s]\n 33%|███▎ | 66/200 [02:19<03:33, 1.59s/it]\n 34%|███▎ | 67/200 [02:19<02:37, 1.18s/it]\n 34%|███▍ | 68/200 [02:22<04:00, 1.82s/it]\n 34%|███▍ | 69/200 [02:25<04:57, 2.27s/it]\n 35%|███▌ | 70/200 [02:29<05:36, 2.59s/it]\n 36%|███▌ | 71/200 [02:29<04:03, 1.89s/it]\n 36%|███▌ | 72/200 [02:29<02:58, 1.39s/it]\n 36%|███▋ | 73/200 [02:29<02:13, 1.05s/it]\n 37%|███▋ | 74/200 [02:30<01:41, 1.24it/s]\n 38%|███▊ | 75/200 [02:33<03:16, 1.58s/it]\n 38%|███▊ | 76/200 [02:33<02:21, 1.14s/it]\n 38%|███▊ | 77/200 [02:37<03:47, 1.85s/it]\n 39%|███▉ | 78/200 [02:40<04:36, 2.27s/it]\n 40%|███▉ | 79/200 [02:43<05:14, 2.60s/it]\n 40%|████ | 80/200 [02:43<03:42, 1.85s/it]\n 40%|████ | 81/200 [02:47<04:33, 2.30s/it]\n 41%|████ | 82/200 [02:50<05:10, 2.63s/it]\n 42%|████▏ | 83/200 [02:53<05:31, 2.84s/it]\n 42%|████▏ | 84/200 [02:54<03:54, 2.02s/it]\n 42%|████▎ | 85/200 [02:57<04:38, 2.42s/it]\n 43%|████▎ | 86/200 [02:57<03:20, 1.76s/it]\n 44%|████▎ | 87/200 [02:57<02:27, 1.31s/it]\n 44%|████▍ | 88/200 [02:58<01:51, 1.01it/s]\n 44%|████▍ | 89/200 [02:58<01:25, 1.30it/s]\n 45%|████▌ | 90/200 [03:01<02:49, 1.54s/it]\n 46%|████▌ | 91/200 [03:05<03:46, 2.07s/it]\n 46%|████▌ | 92/200 [03:08<04:24, 2.45s/it]\n 46%|████▋ | 93/200 [03:08<03:10, 1.78s/it]\n 47%|████▋ | 94/200 [03:11<03:57, 2.24s/it]\n 48%|████▊ | 95/200 [03:15<04:28, 2.56s/it]\n 48%|████▊ | 96/200 [03:15<03:13, 1.86s/it]\n 48%|████▊ | 97/200 [03:15<02:22, 1.38s/it]\n 49%|████▉ | 98/200 [03:19<03:20, 1.96s/it]\n 50%|████▉ | 99/200 [03:22<03:59, 2.37s/it]\n 50%|█████ | 100/200 [03:22<02:52, 1.73s/it]\n 50%|█████ | 101/200 [03:25<03:38, 2.21s/it]\n 51%|█████ | 102/200 [03:29<04:09, 2.54s/it]\n 52%|█████▏ | 103/200 [03:29<02:59, 1.85s/it]\n 52%|█████▏ | 104/200 [03:32<03:42, 2.31s/it]\n 52%|█████▎ | 105/200 [03:33<02:40, 1.69s/it]\n 53%|█████▎ | 106/200 [03:36<03:26, 2.20s/it]\n 54%|█████▎ | 107/200 [03:39<03:55, 2.54s/it]\n 54%|█████▍ | 108/200 [03:39<02:46, 1.81s/it]\n 55%|█████▍ | 109/200 [03:43<03:30, 2.31s/it]\n 55%|█████▌ | 110/200 [03:43<02:28, 1.65s/it]\n 56%|█████▌ | 111/200 [03:46<03:11, 2.15s/it]\n 56%|█████▌ | 112/200 [03:50<03:43, 2.53s/it]\n 56%|█████▋ | 113/200 [03:53<04:00, 2.76s/it]\n 57%|█████▋ | 114/200 [03:53<02:49, 1.97s/it]\n 57%|█████▊ | 115/200 [03:53<02:03, 1.45s/it]\n 58%|█████▊ | 116/200 [03:57<02:49, 2.02s/it]\n 58%|█████▊ | 117/200 [03:57<02:02, 1.48s/it]\n 59%|█████▉ | 118/200 [04:00<02:46, 2.03s/it]\n 60%|█████▉ | 119/200 [04:01<02:00, 1.49s/it]\n 60%|██████ | 120/200 [04:04<02:44, 2.06s/it]\n 60%|██████ | 121/200 [04:07<03:14, 2.46s/it]\n 61%|██████ | 122/200 [04:11<03:32, 2.72s/it]\n 62%|██████▏ | 123/200 [04:14<03:44, 2.92s/it]\n 62%|██████▏ | 124/200 [04:14<02:38, 2.08s/it]\n 62%|██████▎ | 125/200 [04:14<01:54, 1.53s/it]\n 63%|██████▎ | 126/200 [04:18<02:32, 2.06s/it]\n 64%|██████▎ | 127/200 [04:18<01:49, 1.51s/it]\n 64%|██████▍ | 128/200 [04:18<01:21, 1.13s/it]\n 64%|██████▍ | 129/200 [04:18<01:01, 1.16it/s]\n 65%|██████▌ | 130/200 [04:22<01:51, 1.60s/it]\n 66%|██████▌ | 131/200 [04:25<02:25, 2.11s/it]\n 66%|██████▌ | 132/200 [04:25<01:45, 1.55s/it]\n 66%|██████▋ | 133/200 [04:29<02:20, 2.09s/it]\n 67%|██████▋ | 134/200 [04:32<02:43, 2.48s/it]\n 68%|██████▊ | 135/200 [04:32<01:55, 1.78s/it]\n 68%|██████▊ | 136/200 [04:32<01:24, 1.31s/it]\n 68%|██████▊ | 137/200 [04:36<02:02, 1.94s/it]\n 69%|██████▉ | 138/200 [04:36<01:28, 1.43s/it]\n 70%|██████▉ | 139/200 [04:39<02:01, 1.99s/it]\n 70%|███████ | 140/200 [04:43<02:25, 2.42s/it]\n 70%|███████ | 141/200 [04:46<02:38, 2.69s/it]\n 71%|███████ | 142/200 [04:49<02:47, 2.89s/it]\n 72%|███████▏ | 143/200 [04:50<01:57, 2.06s/it]\n 72%|███████▏ | 144/200 [04:50<01:24, 1.52s/it]\n 72%|███████▎ | 145/200 [04:53<01:53, 2.06s/it]\n 73%|███████▎ | 146/200 [04:57<02:12, 2.46s/it]\n 74%|███████▎ | 147/200 [05:00<02:23, 2.70s/it]\n 74%|███████▍ | 148/200 [05:00<01:41, 1.96s/it]\n 74%|███████▍ | 149/200 [05:00<01:13, 1.45s/it]\n 75%|███████▌ | 150/200 [05:01<00:54, 1.09s/it]\n 76%|███████▌ | 151/200 [05:04<01:26, 1.76s/it]\n 76%|███████▌ | 152/200 [05:07<01:46, 2.22s/it]\n 76%|███████▋ | 153/200 [05:07<01:16, 1.63s/it]\n 77%|███████▋ | 154/200 [05:11<01:38, 2.14s/it]\n 78%|███████▊ | 155/200 [05:11<01:10, 1.57s/it]\n 78%|███████▊ | 156/200 [05:11<00:51, 1.17s/it]\n 78%|███████▊ | 157/200 [05:11<00:38, 1.12it/s]\n 79%|███████▉ | 158/200 [05:12<00:27, 1.51it/s]\n 80%|███████▉ | 159/200 [05:15<00:59, 1.46s/it]\n 80%|████████ | 160/200 [05:18<01:21, 2.04s/it]\n 80%|████████ | 161/200 [05:18<00:57, 1.47s/it]\n 81%|████████ | 162/200 [05:22<01:18, 2.06s/it]\n 82%|████████▏ | 163/200 [05:22<00:54, 1.48s/it]\n 82%|████████▏ | 164/200 [05:25<01:14, 2.06s/it]\n 82%|████████▎ | 165/200 [05:26<00:52, 1.51s/it]\n 83%|████████▎ | 166/200 [05:26<00:38, 1.13s/it]\n 84%|████████▎ | 167/200 [05:26<00:28, 1.16it/s]\n 84%|████████▍ | 168/200 [05:29<00:50, 1.59s/it]\n 84%|████████▍ | 169/200 [05:33<01:05, 2.11s/it]\n 85%|████████▌ | 170/200 [05:36<01:14, 2.48s/it]\n 86%|████████▌ | 171/200 [05:36<00:52, 1.81s/it]\n 86%|████████▌ | 172/200 [05:40<01:03, 2.25s/it]\n 86%|████████▋ | 173/200 [05:40<00:44, 1.64s/it]\n 87%|████████▋ | 174/200 [05:40<00:31, 1.22s/it]\n 88%|████████▊ | 175/200 [05:40<00:23, 1.07it/s]\n 88%|████████▊ | 176/200 [05:41<00:17, 1.37it/s]\n 88%|████████▊ | 177/200 [05:41<00:12, 1.82it/s]\n 89%|████████▉ | 178/200 [05:44<00:30, 1.38s/it]\n 90%|████████▉ | 179/200 [05:47<00:41, 1.99s/it]\n 90%|█████████ | 180/200 [05:51<00:47, 2.39s/it]\n 90%|█████████ | 181/200 [05:51<00:32, 1.71s/it]\n 91%|█████████ | 182/200 [05:54<00:39, 2.22s/it]\n 92%|█████████▏| 183/200 [05:54<00:26, 1.59s/it]\n 92%|█████████▏| 184/200 [05:55<00:18, 1.18s/it]\n 92%|█████████▎| 185/200 [05:58<00:27, 1.83s/it]\n 93%|█████████▎| 186/200 [06:01<00:31, 2.28s/it]\n 94%|█████████▎| 187/200 [06:05<00:34, 2.63s/it]\n 94%|█████████▍| 188/200 [06:05<00:22, 1.87s/it]\n 94%|█████████▍| 189/200 [06:08<00:25, 2.32s/it]\n 95%|█████████▌| 190/200 [06:09<00:16, 1.69s/it]\n 96%|█████████▌| 191/200 [06:12<00:19, 2.22s/it]\n 96%|█████████▌| 192/200 [06:12<00:12, 1.59s/it]\n 96%|█████████▋| 193/200 [06:12<00:08, 1.19s/it]\n 97%|█████████▋| 194/200 [06:16<00:11, 1.85s/it]\n 98%|█████████▊| 195/200 [06:19<00:11, 2.32s/it]\n 98%|█████████▊| 196/200 [06:19<00:06, 1.66s/it]\n 98%|█████████▊| 197/200 [06:23<00:06, 2.16s/it]\n 99%|█████████▉| 198/200 [06:23<00:03, 1.58s/it]\n100%|█████████▉| 199/200 [06:23<00:01, 1.18s/it]\n100%|██████████| 200/200 [06:23<00:00, 1.12it/s]\n100%|██████████| 200/200 [06:23<00:00, 1.92s/it]\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1751865433/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_1751865433/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_1751865433/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_1751865433/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 (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : 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"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"error":"Exception : could not broadcast input array from shape (2,) into shape (1,)"}\')\nRequest failed with: (500, \'{"error":"Exception : 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 : negative dimensions are not allowed"}\')\nRequest failed with: (500, \'{"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 (0,)"}\')\n### Batch size: 1 ###\n\ntotal requests 200\nduration (s): 383.78560853004456\nerrors 91\nmean length: 1.635\n\nthroughput (request / second): 0.521124282815162\nthroughput (character / second): 0.8520382024027899\naverage request duration (s) 1.9188248777389527\n50%ile request duration (s) 3.2945549488067627\n75%ile request duration (s) 3.3320202827453613\n90%ile request duration (s) 3.3970138311386107\n95%ile request duration (s) 3.425419509410858\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-llama-8b-nis-800k-9881-v2-profiler is running
Tearing down inference service chaiml-llama-8b-nis-800k-9881-v2-profiler
Service chaiml-llama-8b-nis-800k-9881-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.58s
Shutdown handler de-registered
chaiml-llama-8b-nis-800k_9881_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-llama-8b-nis-800k_9881_v2 status is now torndown due to DeploymentManager action