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 rirv938-llama-8b-pairwis-8323-v1-mkmlizer
Waiting for job on rirv938-llama-8b-pairwis-8323-v1-mkmlizer to finish
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ /___/ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: Downloaded to shared memory in 33.637s
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpgrouevuw, device:0
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: quantized model in 87.842s
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: Processed model rirv938/llama_8b_pairwise_64m_256_tokens_step_31248 in 121.479s
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-8323-v1
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-8323-v1/config.json
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-8323-v1/special_tokens_map.json
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-8323-v1/tokenizer_config.json
rirv938-llama-8b-pairwis-8323-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-8323-v1/flywheel_model.0.safetensors
rirv938-llama-8b-pairwis-8323-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 3/291 [00:00<00:57, 5.02it/s]
Loading 0: 1%|▏ | 4/291 [00:01<01:33, 3.07it/s]
Loading 0: 2%|▏ | 5/291 [00:01<02:05, 2.28it/s]
Loading 0: 3%|▎ | 8/291 [00:02<01:04, 4.37it/s]
Loading 0: 3%|▎ | 9/291 [00:02<01:03, 4.44it/s]
Loading 0: 3%|▎ | 10/291 [00:02<00:55, 5.04it/s]
Loading 0: 4%|▍ | 12/291 [00:03<01:06, 4.16it/s]
Loading 0: 4%|▍ | 13/291 [00:03<01:28, 3.13it/s]
Loading 0: 5%|▍ | 14/291 [00:04<01:52, 2.46it/s]
Loading 0: 6%|▌ | 17/291 [00:04<01:04, 4.23it/s]
Loading 0: 6%|▌ | 18/291 [00:04<01:01, 4.47it/s]
Loading 0: 7%|▋ | 19/291 [00:04<00:54, 5.03it/s]
Loading 0: 7%|▋ | 21/291 [00:05<01:04, 4.20it/s]
Loading 0: 8%|▊ | 22/291 [00:05<01:24, 3.19it/s]
Loading 0: 8%|▊ | 23/291 [00:06<01:46, 2.53it/s]
Loading 0: 9%|▉ | 26/291 [00:06<01:01, 4.30it/s]
Loading 0: 9%|▉ | 27/291 [00:07<00:58, 4.52it/s]
Loading 0: 10%|▉ | 28/291 [00:07<00:52, 5.04it/s]
Loading 0: 10%|█ | 30/291 [00:07<01:01, 4.25it/s]
Loading 0: 11%|█ | 31/291 [00:08<01:21, 3.21it/s]
Loading 0: 11%|█ | 32/291 [00:08<01:42, 2.53it/s]
Loading 0: 12%|█▏ | 35/291 [00:09<00:59, 4.32it/s]
Loading 0: 12%|█▏ | 36/291 [00:09<00:57, 4.43it/s]
Loading 0: 13%|█▎ | 37/291 [00:09<00:50, 5.02it/s]
Loading 0: 13%|█▎ | 39/291 [00:10<00:59, 4.22it/s]
Loading 0: 14%|█▎ | 40/291 [00:10<01:18, 3.20it/s]
Loading 0: 14%|█▍ | 41/291 [00:11<01:40, 2.48it/s]
Loading 0: 15%|█▌ | 44/291 [00:11<00:57, 4.27it/s]
Loading 0: 15%|█▌ | 45/291 [00:11<00:54, 4.52it/s]
Loading 0: 16%|█▌ | 46/291 [00:11<00:47, 5.12it/s]
Loading 0: 16%|█▋ | 48/291 [00:12<00:56, 4.28it/s]
Loading 0: 17%|█▋ | 49/291 [00:13<01:14, 3.23it/s]
Loading 0: 17%|█▋ | 50/291 [00:13<01:34, 2.54it/s]
Loading 0: 18%|█▊ | 53/291 [00:13<00:55, 4.32it/s]
Loading 0: 19%|█▊ | 54/291 [00:14<00:52, 4.56it/s]
Loading 0: 19%|█▉ | 55/291 [00:14<00:45, 5.15it/s]
Loading 0: 20%|█▉ | 57/291 [00:14<00:54, 4.27it/s]
Loading 0: 20%|█▉ | 58/291 [00:15<01:12, 3.21it/s]
Loading 0: 20%|██ | 59/291 [00:16<01:32, 2.52it/s]
Loading 0: 21%|██▏ | 62/291 [00:16<00:52, 4.33it/s]
Loading 0: 22%|██▏ | 63/291 [00:16<00:49, 4.56it/s]
Loading 0: 22%|██▏ | 64/291 [00:16<00:44, 5.13it/s]
Loading 0: 23%|██▎ | 66/291 [00:17<00:52, 4.27it/s]
Loading 0: 23%|██▎ | 67/291 [00:17<01:09, 3.22it/s]
Loading 0: 23%|██▎ | 68/291 [00:18<01:28, 2.53it/s]
Loading 0: 24%|██▍ | 71/291 [00:18<00:50, 4.35it/s]
Loading 0: 25%|██▍ | 72/291 [00:18<00:47, 4.59it/s]
Loading 0: 25%|██▌ | 73/291 [00:18<00:42, 5.18it/s]
Loading 0: 26%|██▌ | 75/291 [00:19<00:50, 4.29it/s]
Loading 0: 26%|██▌ | 76/291 [00:20<01:06, 3.23it/s]
Loading 0: 26%|██▋ | 77/291 [00:20<01:23, 2.55it/s]
Loading 0: 27%|██▋ | 80/291 [00:20<00:48, 4.34it/s]
Loading 0: 28%|██▊ | 81/291 [00:21<00:45, 4.57it/s]
Loading 0: 28%|██▊ | 82/291 [00:21<00:40, 5.16it/s]
Loading 0: 29%|██▊ | 83/291 [00:21<00:42, 4.91it/s]
Loading 0: 29%|██▉ | 84/291 [00:22<01:02, 3.29it/s]
Loading 0: 29%|██▉ | 85/291 [00:22<01:18, 2.62it/s]
Loading 0: 30%|██▉ | 86/291 [00:23<01:34, 2.17it/s]
Loading 0: 31%|███ | 89/291 [00:23<00:49, 4.05it/s]
Loading 0: 31%|███ | 90/291 [00:23<00:45, 4.39it/s]
Loading 0: 31%|███▏ | 91/291 [00:23<00:39, 5.00it/s]
Loading 0: 32%|███▏ | 93/291 [00:24<00:47, 4.19it/s]
Loading 0: 32%|███▏ | 94/291 [00:24<01:02, 3.15it/s]
Loading 0: 33%|███▎ | 95/291 [00:25<01:18, 2.49it/s]
Loading 0: 34%|███▎ | 98/291 [00:25<00:44, 4.33it/s]
Loading 0: 34%|███▍ | 99/291 [00:25<00:42, 4.57it/s]
Loading 0: 34%|███▍ | 100/291 [00:26<00:37, 5.14it/s]
Loading 0: 35%|███▌ | 102/291 [00:26<00:44, 4.28it/s]
Loading 0: 35%|███▌ | 103/291 [00:27<00:58, 3.22it/s]
Loading 0: 36%|███▌ | 104/291 [00:27<01:13, 2.54it/s]
Loading 0: 37%|███▋ | 107/291 [00:28<00:42, 4.34it/s]
Loading 0: 37%|███▋ | 108/291 [00:28<00:39, 4.58it/s]
Loading 0: 37%|███▋ | 109/291 [00:28<00:35, 5.17it/s]
Loading 0: 38%|███▊ | 111/291 [00:28<00:41, 4.30it/s]
Loading 0: 38%|███▊ | 112/291 [00:29<00:55, 3.23it/s]
Loading 0: 39%|███▉ | 113/291 [00:30<01:09, 2.55it/s]
Loading 0: 40%|███▉ | 116/291 [00:30<00:40, 4.33it/s]
Loading 0: 40%|████ | 117/291 [00:30<00:38, 4.56it/s]
Loading 0: 41%|████ | 118/291 [00:30<00:33, 5.15it/s]
Loading 0: 41%|████ | 120/291 [00:31<00:39, 4.29it/s]
Loading 0: 42%|████▏ | 121/291 [00:31<00:52, 3.23it/s]
Loading 0: 42%|████▏ | 122/291 [00:32<01:05, 2.56it/s]
Loading 0: 43%|████▎ | 125/291 [00:32<00:37, 4.39it/s]
Loading 0: 43%|████▎ | 126/291 [00:32<00:35, 4.62it/s]
Loading 0: 44%|████▎ | 127/291 [00:33<00:31, 5.21it/s]
Loading 0: 44%|████▍ | 129/291 [00:33<00:37, 4.31it/s]
Loading 0: 45%|████▍ | 130/291 [00:34<00:49, 3.24it/s]
Loading 0: 45%|████▌ | 131/291 [00:34<01:03, 2.54it/s]
Loading 0: 46%|████▌ | 134/291 [00:35<00:35, 4.37it/s]
Loading 0: 46%|████▋ | 135/291 [00:35<00:33, 4.60it/s]
Loading 0: 47%|████▋ | 136/291 [00:35<00:29, 5.19it/s]
Loading 0: 47%|████▋ | 138/291 [00:35<00:35, 4.30it/s]
Loading 0: 48%|████▊ | 139/291 [00:36<00:46, 3.24it/s]
Loading 0: 48%|████▊ | 140/291 [00:37<00:59, 2.54it/s]
Loading 0: 49%|████▉ | 143/291 [00:37<00:33, 4.37it/s]
Loading 0: 49%|████▉ | 144/291 [00:37<00:31, 4.60it/s]
Loading 0: 50%|████▉ | 145/291 [00:37<00:28, 5.17it/s]
Loading 0: 51%|█████ | 147/291 [00:38<00:33, 4.29it/s]
Loading 0: 51%|█████ | 148/291 [00:38<00:44, 3.24it/s]
Loading 0: 51%|█████ | 149/291 [00:39<00:55, 2.57it/s]
Loading 0: 52%|█████▏ | 152/291 [00:39<00:31, 4.35it/s]
Loading 0: 53%|█████▎ | 153/291 [00:39<00:30, 4.59it/s]
Loading 0: 53%|█████▎ | 154/291 [00:40<00:26, 5.18it/s]
Loading 0: 54%|█████▎ | 156/291 [00:40<00:31, 4.30it/s]
Loading 0: 54%|█████▍ | 157/291 [00:41<00:41, 3.25it/s]
Loading 0: 54%|█████▍ | 158/291 [00:41<00:51, 2.57it/s]
Loading 0: 55%|█████▌ | 161/291 [00:42<00:29, 4.36it/s]
Loading 0: 56%|█████▌ | 162/291 [00:42<00:28, 4.59it/s]
Loading 0: 56%|█████▌ | 163/291 [00:42<00:24, 5.18it/s]
Loading 0: 57%|█████▋ | 165/291 [00:42<00:29, 4.32it/s]
Loading 0: 57%|█████▋ | 166/291 [00:43<00:38, 3.27it/s]
Loading 0: 57%|█████▋ | 167/291 [00:44<00:48, 2.57it/s]
Loading 0: 58%|█████▊ | 170/291 [00:44<00:27, 4.41it/s]
Loading 0: 59%|█████▉ | 171/291 [00:44<00:25, 4.64it/s]
Loading 0: 59%|█████▉ | 172/291 [00:44<00:23, 5.15it/s]
Loading 0: 59%|█████▉ | 173/291 [00:45<00:33, 3.48it/s]
Loading 0: 60%|██████ | 175/291 [00:45<00:24, 4.69it/s]
Loading 0: 60%|██████ | 176/291 [00:45<00:23, 4.92it/s]
Loading 0: 61%|██████ | 177/291 [00:45<00:20, 5.58it/s]
Loading 0: 62%|██████▏ | 179/291 [00:46<00:25, 4.39it/s]
Loading 0: 62%|██████▏ | 180/291 [00:46<00:34, 3.23it/s]
Loading 0: 62%|██████▏ | 181/291 [00:47<00:43, 2.52it/s]
Loading 0: 63%|██████▎ | 184/291 [00:47<00:24, 4.36it/s]
Loading 0: 64%|██████▎ | 185/291 [00:47<00:23, 4.59it/s]
Loading 0: 64%|██████▍ | 186/291 [00:48<00:20, 5.15it/s]
Loading 0: 64%|██████▍ | 187/291 [00:48<00:20, 5.03it/s]
Loading 0: 65%|██████▍ | 188/291 [00:48<00:30, 3.36it/s]
Loading 0: 65%|██████▍ | 189/291 [00:49<00:40, 2.54it/s]
Loading 0: 66%|██████▌ | 192/291 [00:50<00:28, 3.47it/s]
Loading 0: 66%|██████▋ | 193/291 [00:50<00:34, 2.87it/s]
Loading 0: 67%|██████▋ | 194/291 [00:51<00:40, 2.39it/s]
Loading 0: 68%|██████▊ | 197/291 [00:51<00:23, 4.04it/s]
Loading 0: 68%|██████▊ | 198/291 [00:51<00:21, 4.29it/s]
Loading 0: 68%|██████▊ | 199/291 [00:51<00:19, 4.83it/s]
Loading 0: 69%|██████▉ | 201/291 [00:52<00:21, 4.17it/s]
Loading 0: 69%|██████▉ | 202/291 [00:52<00:27, 3.19it/s]
Loading 0: 70%|██████▉ | 203/291 [00:53<00:34, 2.53it/s]
Loading 0: 71%|███████ | 206/291 [00:53<00:19, 4.33it/s]
Loading 0: 71%|███████ | 207/291 [00:54<00:18, 4.57it/s]
Loading 0: 71%|███████▏ | 208/291 [00:54<00:16, 5.15it/s]
Loading 0: 72%|███████▏ | 210/291 [00:54<00:18, 4.29it/s]
Loading 0: 73%|███████▎ | 211/291 [00:55<00:24, 3.24it/s]
Loading 0: 73%|███████▎ | 212/291 [00:55<00:30, 2.57it/s]
Loading 0: 74%|███████▍ | 215/291 [00:56<00:17, 4.41it/s]
Loading 0: 74%|███████▍ | 216/291 [00:56<00:16, 4.64it/s]
Loading 0: 75%|███████▍ | 217/291 [00:56<00:14, 5.17it/s]
Loading 0: 75%|███████▌ | 219/291 [00:57<00:16, 4.30it/s]
Loading 0: 76%|███████▌ | 220/291 [00:57<00:21, 3.24it/s]
Loading 0: 76%|███████▌ | 221/291 [00:58<00:27, 2.56it/s]
Loading 0: 77%|███████▋ | 224/291 [00:58<00:15, 4.37it/s]
Loading 0: 77%|███████▋ | 225/291 [00:58<00:14, 4.67it/s]
Loading 0: 78%|███████▊ | 226/291 [00:58<00:12, 5.24it/s]
Loading 0: 78%|███████▊ | 228/291 [00:59<00:14, 4.31it/s]
Loading 0: 79%|███████▊ | 229/291 [00:59<00:19, 3.24it/s]
Loading 0: 79%|███████▉ | 230/291 [01:00<00:23, 2.56it/s]
Loading 0: 80%|████████ | 233/291 [01:00<00:13, 4.40it/s]
Loading 0: 80%|████████ | 234/291 [01:00<00:12, 4.62it/s]
Loading 0: 81%|████████ | 235/291 [01:01<00:10, 5.18it/s]
Loading 0: 81%|████████▏ | 237/291 [01:01<00:12, 4.28it/s]
Loading 0: 82%|████████▏ | 238/291 [01:02<00:16, 3.24it/s]
Loading 0: 82%|████████▏ | 239/291 [01:02<00:20, 2.56it/s]
Loading 0: 83%|████████▎ | 242/291 [01:03<00:11, 4.40it/s]
Loading 0: 84%|████████▎ | 243/291 [01:03<00:10, 4.62it/s]
Loading 0: 84%|████████▍ | 244/291 [01:03<00:09, 5.18it/s]
Loading 0: 85%|████████▍ | 246/291 [01:03<00:10, 4.29it/s]
Loading 0: 85%|████████▍ | 247/291 [01:04<00:13, 3.24it/s]
Loading 0: 85%|████████▌ | 248/291 [01:05<00:16, 2.57it/s]
Loading 0: 86%|████████▋ | 251/291 [01:05<00:09, 4.36it/s]
Loading 0: 87%|████████▋ | 252/291 [01:05<00:08, 4.59it/s]
Loading 0: 87%|████████▋ | 253/291 [01:05<00:07, 5.14it/s]
Loading 0: 88%|████████▊ | 255/291 [01:06<00:08, 4.29it/s]
Loading 0: 88%|████████▊ | 256/291 [01:06<00:10, 3.24it/s]
Loading 0: 88%|████████▊ | 257/291 [01:07<00:13, 2.56it/s]
Loading 0: 89%|████████▉ | 260/291 [01:07<00:07, 4.35it/s]
Loading 0: 90%|████████▉ | 261/291 [01:07<00:06, 4.56it/s]
Loading 0: 90%|█████████ | 262/291 [01:08<00:05, 5.06it/s]
Loading 0: 91%|█████████ | 264/291 [01:08<00:06, 4.24it/s]
Loading 0: 91%|█████████ | 265/291 [01:09<00:08, 3.16it/s]
Loading 0: 91%|█████████▏| 266/291 [01:09<00:09, 2.52it/s]
Loading 0: 92%|█████████▏| 269/291 [01:10<00:05, 4.34it/s]
Loading 0: 93%|█████████▎| 270/291 [01:10<00:04, 4.55it/s]
Loading 0: 93%|█████████▎| 271/291 [01:10<00:03, 5.14it/s]
Loading 0: 94%|█████████▍| 273/291 [01:10<00:04, 4.31it/s]
Loading 0: 94%|█████████▍| 274/291 [01:11<00:05, 3.26it/s]
Loading 0: 95%|█████████▍| 275/291 [01:12<00:06, 2.59it/s]
Loading 0: 96%|█████████▌| 278/291 [01:12<00:02, 4.40it/s]
Loading 0: 96%|█████████▌| 279/291 [01:12<00:02, 4.64it/s]
Loading 0: 96%|█████████▌| 280/291 [01:12<00:02, 5.22it/s]
Loading 0: 97%|█████████▋| 281/291 [01:13<00:02, 3.50it/s]
Loading 0: 97%|█████████▋| 282/291 [01:13<00:03, 2.64it/s]
Loading 0: 98%|█████████▊| 284/291 [01:14<00:01, 3.80it/s]
Loading 0: 98%|█████████▊| 285/291 [01:14<00:01, 4.14it/s]
Loading 0: 98%|█████████▊| 286/291 [01:14<00:01, 4.82it/s]
Loading 0: 99%|█████████▊| 287/291 [01:14<00:00, 4.90it/s]
Loading 0: 99%|█████████▉| 288/291 [01:15<00:00, 3.24it/s]
Job rirv938-llama-8b-pairwis-8323-v1-mkmlizer completed after 156.19s with status: succeeded
Stopping job with name rirv938-llama-8b-pairwis-8323-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.74s
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 rirv938-llama-8b-pairwis-8323-v1
Waiting for inference service rirv938-llama-8b-pairwis-8323-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-llama-8b-pairwis-8323-v1 ready after 200.68638396263123s
Pipeline stage MKMLDeployer completed in 201.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 7.72161602973938s
Received healthy response to inference request in 3.0381429195404053s
Received healthy response to inference request in 3.13219952583313s
Received healthy response to inference request in 3.0855698585510254s
Received healthy response to inference request in 5.039956569671631s
5 requests
0 failed requests
5th percentile: 3.047628307342529
10th percentile: 3.057113695144653
20th percentile: 3.0760844707489015
30th percentile: 3.0948957920074465
40th percentile: 3.113547658920288
50th percentile: 3.13219952583313
60th percentile: 3.89530234336853
70th percentile: 4.65840516090393
80th percentile: 5.576288461685181
90th percentile: 6.64895224571228
95th percentile: 7.18528413772583
99th percentile: 7.61434965133667
mean time: 4.403496980667114
%s, retrying in %s seconds...
Received healthy response to inference request in 5.146164178848267s
Received healthy response to inference request in 2.4688732624053955s
Received healthy response to inference request in 4.137641429901123s
Received healthy response to inference request in 3.996866226196289s
Received healthy response to inference request in 3.47019100189209s
5 requests
0 failed requests
5th percentile: 2.669136810302734
10th percentile: 2.8694003582000733
20th percentile: 3.269927453994751
30th percentile: 3.5755260467529295
40th percentile: 3.7861961364746093
50th percentile: 3.996866226196289
60th percentile: 4.053176307678223
70th percentile: 4.109486389160156
80th percentile: 4.339345979690552
90th percentile: 4.7427550792694095
95th percentile: 4.944459629058838
99th percentile: 5.105823268890381
mean time: 3.8439472198486326
%s, retrying in %s seconds...
Received healthy response to inference request in 3.6449995040893555s
Received healthy response to inference request in 3.6632416248321533s
Received healthy response to inference request in 2.6308326721191406s
Received healthy response to inference request in 3.432410478591919s
Received healthy response to inference request in 2.212101936340332s
5 requests
0 failed requests
5th percentile: 2.295848083496094
10th percentile: 2.3795942306518554
20th percentile: 2.5470865249633787
30th percentile: 2.791148233413696
40th percentile: 3.1117793560028075
50th percentile: 3.432410478591919
60th percentile: 3.5174460887908934
70th percentile: 3.6024816989898683
80th percentile: 3.648647928237915
90th percentile: 3.6559447765350344
95th percentile: 3.659593200683594
99th percentile: 3.6625119400024415
mean time: 3.11671724319458
Pipeline stage StressChecker completed in 60.81s
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 2.25s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.03s
Shutdown handler de-registered
rirv938-llama-8b-pairwis_8323_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 0.15s
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 rirv938-llama-8b-pairwis-8323-v1-profiler
Waiting for inference service rirv938-llama-8b-pairwis-8323-v1-profiler to be ready
Inference service rirv938-llama-8b-pairwis-8323-v1-profiler ready after 200.48271203041077s
Pipeline stage MKMLProfilerDeployer completed in 200.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploftxgr:/code/chaiverse_profiler_1734034428 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploftxgr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734034428 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734034428/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploftxgr:/code/chaiverse_profiler_1734037214 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploftxgr:/code/chaiverse_profiler_1734037215 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploftxgr --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734037215 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734037215/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-8323-v1-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-8323-v1-profiler
Service rirv938-llama-8b-pairwis-8323-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.28s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-8323-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.37s
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 rirv938-llama-8b-pairwis-8323-v1-profiler
Waiting for inference service rirv938-llama-8b-pairwis-8323-v1-profiler to be ready
Inference service rirv938-llama-8b-pairwis-8323-v1-profiler ready after 70.21930289268494s
Pipeline stage MKMLProfilerDeployer completed in 70.55s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploxllr5:/code/chaiverse_profiler_1734037928 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploxllr5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734037928 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734037928/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploxllr5:/code/chaiverse_profiler_1734040704 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deploxllr5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734040704 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734040704/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-8323-v1-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-8323-v1-profiler
Service rirv938-llama-8b-pairwis-8323-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.23s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-8323-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.46s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-pairwis-8323-v1-profiler
Waiting for inference service rirv938-llama-8b-pairwis-8323-v1-profiler to be ready
Inference service rirv938-llama-8b-pairwis-8323-v1-profiler ready after 120.34770584106445s
Pipeline stage MKMLProfilerDeployer completed in 120.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deplov9dsb:/code/chaiverse_profiler_1734041609 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deplov9dsb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734041609 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734041609/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deplov9dsb:/code/chaiverse_profiler_1734044385 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deplov9dsb:/code/chaiverse_profiler_1734044386 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-paid266be1cb527aa16fe5150147b5bec84-deplov9dsb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734044386 && 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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1734044386/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-8323-v1-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-8323-v1-profiler
Service rirv938-llama-8b-pairwis-8323-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.27s
Shutdown handler de-registered
rirv938-llama-8b-pairwis_8323_v1 status is now inactive due to auto deactivation removed underperforming models