junhua024-chai-16-full-qkv_72

developer_uid: junhua024
submission_id: junhua024-chai-16-full-qkv_72_v7
model_name: junhua024-chai-16-full-qkv_72_v7
model_group: junhua024/chai_16_full_q
status: torndown
timestamp: 2025-07-21T05:56:28+00:00
num_battles: 8460
num_wins: 4083
celo_rating: 1274.51
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1624
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.599751462790428, 'latency_mean': 1.6671653807163238, 'latency_p50': 1.6570684909820557, 'latency_p90': 1.835024857521057}, {'batch_size': 3, 'throughput': 1.0772831311602584, 'latency_mean': 2.7717780375480654, 'latency_p50': 2.7886420488357544, 'latency_p90': 3.0582273483276365}, {'batch_size': 5, 'throughput': 1.2938197603814958, 'latency_mean': 3.8460985004901884, 'latency_p50': 3.8736766576766968, 'latency_p90': 4.32309136390686}, {'batch_size': 6, 'throughput': 1.3623259765667879, 'latency_mean': 4.382457382678986, 'latency_p50': 4.398292899131775, 'latency_p90': 4.831736445426941}, {'batch_size': 8, 'throughput': 1.4239595100896134, 'latency_mean': 5.577041838169098, 'latency_p50': 5.605814695358276, 'latency_p90': 6.2506123065948485}, {'batch_size': 10, 'throughput': 1.458455914379251, 'latency_mean': 6.807600156068802, 'latency_p50': 6.791633486747742, 'latency_p90': 7.666928124427796}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-qkv_72_v7
is_internal_developer: False
language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-07-20
win_ratio: 0.4826241134751773
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 10, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
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 junhua024-chai-16-full-qkv-72-v7-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v7-mkmlizer to finish
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Downloaded to shared memory in 79.540s
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1624 already exists in ChaiML
junhua024-chai-16-full-qkv-72-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxfydi9ym, device:0
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-qkv-72-v7-mkmlizer: quantized model in 30.983s
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1624 in 110.613s
junhua024-chai-16-full-qkv-72-v7-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia
junhua024-chai-16-full-qkv-72-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia/config.json
junhua024-chai-16-full-qkv-72-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia/tokenizer.json
junhua024-chai-16-full-qkv-72-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v7/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-qkv-72-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 15.94it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 17.99it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.02it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.07it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.93it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.23it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:09, 33.48it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 34.56it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 42.87it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 35.15it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.47it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.16it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.08it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.53it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.14it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.54it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 38.53it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 38.89it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:06, 37.85it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:07, 36.52it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 41.00it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.96it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.32it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 35.73it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.52it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.96it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 35.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 40.70it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 38.09it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 37.43it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 35.45it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 42.45it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.91it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 35.56it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 37.25it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 35.41it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 38.55it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 38.11it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 33.23it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 31.81it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 43.13it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 32.83it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 33.04it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.42it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 34.17it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 32.98it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.93it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 32.22it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 33.17it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.28it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 33.99it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 39.42it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 37.27it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 36.95it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 34.00it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 40.77it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 33.79it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.39it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 36.00it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.72it/s]
Loading 0:  90%|████████▉ | 326/363 [00:09<00:00, 37.72it/s]
Loading 0:  91%|█████████ | 331/363 [00:09<00:00, 36.09it/s]
Loading 0:  93%|█████████▎| 336/363 [00:09<00:00, 37.61it/s]
Loading 0:  94%|█████████▎| 340/363 [00:09<00:00, 36.33it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 41.87it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 22.77it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 24.87it/s]
Loading 0:  99%|█████████▉| 359/363 [00:10<00:00, 26.79it/s]
                                                            
Job junhua024-chai-16-full-qkv-72-v7-mkmlizer completed after 139.77s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v7-mkmlizer
Pipeline stage MKMLizer completed in 140.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v7
Waiting for inference service junhua024-chai-16-full-qkv-72-v7 to be ready
Failed to get response for submission zhouzr-sft-chai50-sodasmall_v1: HTTPConnectionPool(host='zhouzr-sft-chai50-sodasmall-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zhouzr-sft-chai50-sodasmall_v1: HTTPConnectionPool(host='zhouzr-sft-chai50-sodasmall-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zhouzr-sft-chai50-sodasmall_v1: HTTPConnectionPool(host='zhouzr-sft-chai50-sodasmall-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zhouzr-sft-chai50-sodasmall_v1: HTTPConnectionPool(host='zhouzr-sft-chai50-sodasmall-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission zhouzr-sft-chai50-sodasmall_v1: HTTPConnectionPool(host='zhouzr-sft-chai50-sodasmall-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-qkv-72-v7 ready after 321.4000952243805s
Pipeline stage MKMLDeployer completed in 321.93s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3863887786865234s
Received healthy response to inference request in 1.828188419342041s
Received healthy response to inference request in 2.5303826332092285s
Received healthy response to inference request in 1.661210060119629s
Received healthy response to inference request in 1.5349195003509521s
5 requests
0 failed requests
5th percentile: 1.5601776123046875
10th percentile: 1.585435724258423
20th percentile: 1.6359519481658935
30th percentile: 1.6946057319641112
40th percentile: 1.7613970756530761
50th percentile: 1.828188419342041
60th percentile: 2.051468563079834
70th percentile: 2.274748706817627
80th percentile: 2.4151875495910646
90th percentile: 2.4727850914001466
95th percentile: 2.5015838623046873
99th percentile: 2.5246228790283203
mean time: 1.9882178783416748
Pipeline stage StressChecker completed in 11.47s
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 0.67s
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 0.69s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v7 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
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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v7-profiler
Waiting for inference service junhua024-chai-16-full-qkv-72-v7-profiler to be ready
Inference service junhua024-chai-16-full-qkv-72-v7-profiler ready after 323.46529030799866s
Pipeline stage MKMLProfilerDeployer completed in 324.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/junhua024-chai-16-fua5fcf40dcf763a4269ee666eb90e2441-deplo5plrq:/code/chaiverse_profiler_1753078292 --namespace tenant-chaiml-guanaco
kubectl exec -it junhua024-chai-16-fua5fcf40dcf763a4269ee666eb90e2441-deplo5plrq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1753078292 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1753078292/summary.json'
kubectl exec -it junhua024-chai-16-fua5fcf40dcf763a4269ee666eb90e2441-deplo5plrq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1753078292/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1110.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service junhua024-chai-16-full-qkv-72-v7-profiler is running
Tearing down inference service junhua024-chai-16-full-qkv-72-v7-profiler
Service junhua024-chai-16-full-qkv-72-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 4.57s
Shutdown handler de-registered
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...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v7 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v7 status is now torndown due to DeploymentManager action