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-6659-v7-mkmlizer
Waiting for job on rirv938-llama-8b-pairwis-6659-v7-mkmlizer to finish
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ /___/ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ Version: 0.11.12 ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ║ ║
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: Downloaded to shared memory in 24.393s
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp16jyjnc2, device:0
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: quantized model in 86.783s
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: Processed model rirv938/llama_8b_pairwise_64m_256_tokens_step_7812 in 111.176s
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7/config.json
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7/special_tokens_map.json
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7/tokenizer_config.json
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7/tokenizer.json
rirv938-llama-8b-pairwis-6659-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-pairwis-6659-v7/flywheel_model.0.safetensors
rirv938-llama-8b-pairwis-6659-v7-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 3/291 [00:00<00:57, 5.01it/s]
Loading 0: 1%|▏ | 4/291 [00:01<01:33, 3.08it/s]
Loading 0: 2%|▏ | 5/291 [00:01<02:04, 2.29it/s]
Loading 0: 3%|▎ | 8/291 [00:02<01:04, 4.41it/s]
Loading 0: 3%|▎ | 9/291 [00:02<01:03, 4.46it/s]
Loading 0: 3%|▎ | 10/291 [00:02<00:55, 5.10it/s]
Loading 0: 4%|▍ | 12/291 [00:02<01:05, 4.24it/s]
Loading 0: 4%|▍ | 13/291 [00:03<01:27, 3.19it/s]
Loading 0: 5%|▍ | 14/291 [00:04<01:49, 2.53it/s]
Loading 0: 6%|▌ | 17/291 [00:04<01:03, 4.34it/s]
Loading 0: 6%|▌ | 18/291 [00:04<00:59, 4.58it/s]
Loading 0: 7%|▋ | 19/291 [00:04<00:52, 5.17it/s]
Loading 0: 7%|▋ | 21/291 [00:05<01:02, 4.30it/s]
Loading 0: 8%|▊ | 22/291 [00:05<01:22, 3.25it/s]
Loading 0: 8%|▊ | 23/291 [00:06<01:45, 2.54it/s]
Loading 0: 9%|▉ | 26/291 [00:06<01:01, 4.33it/s]
Loading 0: 9%|▉ | 27/291 [00:06<00:57, 4.56it/s]
Loading 0: 10%|▉ | 28/291 [00:07<00:50, 5.17it/s]
Loading 0: 10%|█ | 30/291 [00:07<01:00, 4.32it/s]
Loading 0: 11%|█ | 31/291 [00:08<01:19, 3.26it/s]
Loading 0: 11%|█ | 32/291 [00:08<01:41, 2.55it/s]
Loading 0: 12%|█▏ | 35/291 [00:09<00:59, 4.32it/s]
Loading 0: 12%|█▏ | 36/291 [00:09<00:56, 4.53it/s]
Loading 0: 13%|█▎ | 37/291 [00:09<00:50, 5.04it/s]
Loading 0: 13%|█▎ | 39/291 [00:09<00:59, 4.25it/s]
Loading 0: 14%|█▎ | 40/291 [00:10<01:18, 3.21it/s]
Loading 0: 14%|█▍ | 41/291 [00:11<01:38, 2.53it/s]
Loading 0: 15%|█▌ | 44/291 [00:11<00:57, 4.30it/s]
Loading 0: 15%|█▌ | 45/291 [00:11<00:54, 4.52it/s]
Loading 0: 16%|█▌ | 46/291 [00:11<00:47, 5.11it/s]
Loading 0: 16%|█▋ | 48/291 [00:12<00:56, 4.31it/s]
Loading 0: 17%|█▋ | 49/291 [00:12<01:14, 3.26it/s]
Loading 0: 17%|█▋ | 50/291 [00:13<01:33, 2.57it/s]
Loading 0: 18%|█▊ | 53/291 [00:13<00:54, 4.36it/s]
Loading 0: 19%|█▊ | 54/291 [00:13<00:51, 4.60it/s]
Loading 0: 19%|█▉ | 55/291 [00:14<00:45, 5.17it/s]
Loading 0: 20%|█▉ | 57/291 [00:14<00:54, 4.33it/s]
Loading 0: 20%|█▉ | 58/291 [00:15<01:11, 3.28it/s]
Loading 0: 20%|██ | 59/291 [00:15<01:31, 2.54it/s]
Loading 0: 21%|██▏ | 62/291 [00:16<00:53, 4.31it/s]
Loading 0: 22%|██▏ | 63/291 [00:16<00:50, 4.55it/s]
Loading 0: 22%|██▏ | 64/291 [00:16<00:44, 5.13it/s]
Loading 0: 23%|██▎ | 66/291 [00:16<00:52, 4.31it/s]
Loading 0: 23%|██▎ | 67/291 [00:17<01:08, 3.26it/s]
Loading 0: 23%|██▎ | 68/291 [00:18<01:26, 2.57it/s]
Loading 0: 24%|██▍ | 71/291 [00:18<00:49, 4.41it/s]
Loading 0: 25%|██▍ | 72/291 [00:18<00:47, 4.63it/s]
Loading 0: 25%|██▌ | 73/291 [00:18<00:41, 5.21it/s]
Loading 0: 26%|██▌ | 75/291 [00:19<00:49, 4.36it/s]
Loading 0: 26%|██▌ | 76/291 [00:19<01:05, 3.27it/s]
Loading 0: 26%|██▋ | 77/291 [00:20<01:23, 2.56it/s]
Loading 0: 27%|██▋ | 80/291 [00:20<00:48, 4.38it/s]
Loading 0: 28%|██▊ | 81/291 [00:20<00:45, 4.60it/s]
Loading 0: 28%|██▊ | 82/291 [00:20<00:40, 5.19it/s]
Loading 0: 29%|██▊ | 83/291 [00:21<00:40, 5.14it/s]
Loading 0: 29%|██▉ | 84/291 [00:21<01:00, 3.40it/s]
Loading 0: 29%|██▉ | 85/291 [00:22<01:16, 2.68it/s]
Loading 0: 30%|██▉ | 86/291 [00:23<01:33, 2.18it/s]
Loading 0: 31%|███ | 89/291 [00:23<00:50, 4.02it/s]
Loading 0: 31%|███ | 90/291 [00:23<00:46, 4.30it/s]
Loading 0: 31%|███▏ | 91/291 [00:23<00:40, 4.91it/s]
Loading 0: 32%|███▏ | 93/291 [00:24<00:47, 4.19it/s]
Loading 0: 32%|███▏ | 94/291 [00:24<01:01, 3.18it/s]
Loading 0: 33%|███▎ | 95/291 [00:25<01:17, 2.52it/s]
Loading 0: 34%|███▎ | 98/291 [00:25<00:44, 4.32it/s]
Loading 0: 34%|███▍ | 99/291 [00:25<00:42, 4.56it/s]
Loading 0: 34%|███▍ | 100/291 [00:25<00:37, 5.16it/s]
Loading 0: 35%|███▌ | 102/291 [00:26<00:43, 4.32it/s]
Loading 0: 35%|███▌ | 103/291 [00:26<00:57, 3.27it/s]
Loading 0: 36%|███▌ | 104/291 [00:27<01:11, 2.60it/s]
Loading 0: 37%|███▋ | 107/291 [00:27<00:41, 4.45it/s]
Loading 0: 37%|███▋ | 108/291 [00:27<00:39, 4.69it/s]
Loading 0: 37%|███▋ | 109/291 [00:28<00:34, 5.24it/s]
Loading 0: 38%|███▊ | 111/291 [00:28<00:41, 4.36it/s]
Loading 0: 38%|███▊ | 112/291 [00:29<00:54, 3.30it/s]
Loading 0: 39%|███▉ | 113/291 [00:29<01:07, 2.62it/s]
Loading 0: 40%|███▉ | 116/291 [00:30<00:39, 4.43it/s]
Loading 0: 40%|████ | 117/291 [00:30<00:37, 4.66it/s]
Loading 0: 41%|████ | 118/291 [00:30<00:33, 5.20it/s]
Loading 0: 41%|████ | 120/291 [00:30<00:39, 4.33it/s]
Loading 0: 42%|████▏ | 121/291 [00:31<00:53, 3.19it/s]
Loading 0: 42%|████▏ | 122/291 [00:32<01:06, 2.54it/s]
Loading 0: 43%|████▎ | 125/291 [00:32<00:37, 4.37it/s]
Loading 0: 43%|████▎ | 126/291 [00:32<00:35, 4.61it/s]
Loading 0: 44%|████▎ | 127/291 [00:32<00:31, 5.20it/s]
Loading 0: 44%|████▍ | 129/291 [00:33<00:37, 4.35it/s]
Loading 0: 45%|████▍ | 130/291 [00:33<00:48, 3.29it/s]
Loading 0: 45%|████▌ | 131/291 [00:34<01:01, 2.59it/s]
Loading 0: 46%|████▌ | 134/291 [00:34<00:35, 4.45it/s]
Loading 0: 46%|████▋ | 135/291 [00:34<00:33, 4.69it/s]
Loading 0: 47%|████▋ | 136/291 [00:34<00:29, 5.29it/s]
Loading 0: 47%|████▋ | 138/291 [00:35<00:34, 4.39it/s]
Loading 0: 48%|████▊ | 139/291 [00:36<00:46, 3.30it/s]
Loading 0: 48%|████▊ | 140/291 [00:36<00:57, 2.61it/s]
Loading 0: 49%|████▉ | 143/291 [00:36<00:33, 4.42it/s]
Loading 0: 49%|████▉ | 144/291 [00:37<00:31, 4.66it/s]
Loading 0: 50%|████▉ | 145/291 [00:37<00:27, 5.24it/s]
Loading 0: 51%|█████ | 147/291 [00:37<00:32, 4.39it/s]
Loading 0: 51%|█████ | 148/291 [00:38<00:43, 3.30it/s]
Loading 0: 51%|█████ | 149/291 [00:39<00:54, 2.59it/s]
Loading 0: 52%|█████▏ | 152/291 [00:39<00:31, 4.38it/s]
Loading 0: 53%|█████▎ | 153/291 [00:39<00:29, 4.60it/s]
Loading 0: 53%|█████▎ | 154/291 [00:39<00:26, 5.20it/s]
Loading 0: 54%|█████▎ | 156/291 [00:40<00:31, 4.35it/s]
Loading 0: 54%|█████▍ | 157/291 [00:40<00:40, 3.28it/s]
Loading 0: 54%|█████▍ | 158/291 [00:41<00:51, 2.59it/s]
Loading 0: 55%|█████▌ | 161/291 [00:41<00:29, 4.35it/s]
Loading 0: 56%|█████▌ | 162/291 [00:41<00:28, 4.60it/s]
Loading 0: 56%|█████▌ | 163/291 [00:41<00:24, 5.19it/s]
Loading 0: 57%|█████▋ | 165/291 [00:42<00:29, 4.31it/s]
Loading 0: 57%|█████▋ | 166/291 [00:43<00:38, 3.26it/s]
Loading 0: 57%|█████▋ | 167/291 [00:43<00:47, 2.59it/s]
Loading 0: 58%|█████▊ | 170/291 [00:43<00:27, 4.40it/s]
Loading 0: 59%|█████▉ | 171/291 [00:44<00:25, 4.64it/s]
Loading 0: 59%|█████▉ | 172/291 [00:44<00:22, 5.22it/s]
Loading 0: 59%|█████▉ | 173/291 [00:44<00:33, 3.53it/s]
Loading 0: 60%|██████ | 175/291 [00:44<00:24, 4.82it/s]
Loading 0: 60%|██████ | 176/291 [00:45<00:22, 5.03it/s]
Loading 0: 61%|██████ | 177/291 [00:45<00:20, 5.62it/s]
Loading 0: 62%|██████▏ | 179/291 [00:45<00:25, 4.48it/s]
Loading 0: 62%|██████▏ | 180/291 [00:46<00:33, 3.30it/s]
Loading 0: 62%|██████▏ | 181/291 [00:47<00:42, 2.59it/s]
Loading 0: 63%|██████▎ | 184/291 [00:47<00:23, 4.48it/s]
Loading 0: 64%|██████▎ | 185/291 [00:47<00:22, 4.72it/s]
Loading 0: 64%|██████▍ | 186/291 [00:47<00:19, 5.32it/s]
Loading 0: 64%|██████▍ | 187/291 [00:47<00:19, 5.38it/s]
Loading 0: 65%|██████▍ | 188/291 [00:48<00:29, 3.49it/s]
Loading 0: 65%|██████▍ | 189/291 [00:48<00:39, 2.61it/s]
Loading 0: 66%|██████▌ | 192/291 [00:49<00:27, 3.56it/s]
Loading 0: 66%|██████▋ | 193/291 [00:50<00:33, 2.93it/s]
Loading 0: 67%|██████▋ | 194/291 [00:50<00:39, 2.45it/s]
Loading 0: 68%|██████▊ | 197/291 [00:50<00:22, 4.12it/s]
Loading 0: 68%|██████▊ | 198/291 [00:51<00:21, 4.39it/s]
Loading 0: 68%|██████▊ | 199/291 [00:51<00:18, 4.96it/s]
Loading 0: 69%|██████▉ | 201/291 [00:51<00:21, 4.25it/s]
Loading 0: 69%|██████▉ | 202/291 [00:52<00:27, 3.24it/s]
Loading 0: 70%|██████▉ | 203/291 [00:52<00:34, 2.56it/s]
Loading 0: 71%|███████ | 206/291 [00:53<00:19, 4.33it/s]
Loading 0: 71%|███████ | 207/291 [00:53<00:18, 4.58it/s]
Loading 0: 71%|███████▏ | 208/291 [00:53<00:16, 5.15it/s]
Loading 0: 72%|███████▏ | 210/291 [00:54<00:18, 4.33it/s]
Loading 0: 73%|███████▎ | 211/291 [00:54<00:24, 3.27it/s]
Loading 0: 73%|███████▎ | 212/291 [00:55<00:30, 2.59it/s]
Loading 0: 74%|███████▍ | 215/291 [00:55<00:17, 4.45it/s]
Loading 0: 74%|███████▍ | 216/291 [00:55<00:16, 4.69it/s]
Loading 0: 75%|███████▍ | 217/291 [00:55<00:14, 5.22it/s]
Loading 0: 75%|███████▌ | 219/291 [00:56<00:16, 4.35it/s]
Loading 0: 76%|███████▌ | 220/291 [00:56<00:21, 3.27it/s]
Loading 0: 76%|███████▌ | 221/291 [00:57<00:26, 2.61it/s]
Loading 0: 77%|███████▋ | 224/291 [00:57<00:15, 4.42it/s]
Loading 0: 77%|███████▋ | 225/291 [00:57<00:14, 4.66it/s]
Loading 0: 78%|███████▊ | 226/291 [00:58<00:12, 5.25it/s]
Loading 0: 78%|███████▊ | 228/291 [00:58<00:14, 4.36it/s]
Loading 0: 79%|███████▊ | 229/291 [00:59<00:18, 3.30it/s]
Loading 0: 79%|███████▉ | 230/291 [00:59<00:23, 2.62it/s]
Loading 0: 80%|████████ | 233/291 [01:00<00:12, 4.50it/s]
Loading 0: 80%|████████ | 234/291 [01:00<00:12, 4.74it/s]
Loading 0: 81%|████████ | 235/291 [01:00<00:10, 5.30it/s]
Loading 0: 81%|████████▏ | 237/291 [01:00<00:12, 4.41it/s]
Loading 0: 82%|████████▏ | 238/291 [01:01<00:15, 3.32it/s]
Loading 0: 82%|████████▏ | 239/291 [01:02<00:20, 2.59it/s]
Loading 0: 83%|████████▎ | 242/291 [01:02<00:11, 4.41it/s]
Loading 0: 84%|████████▎ | 243/291 [01:02<00:10, 4.65it/s]
Loading 0: 84%|████████▍ | 244/291 [01:02<00:09, 5.21it/s]
Loading 0: 85%|████████▍ | 246/291 [01:03<00:10, 4.36it/s]
Loading 0: 85%|████████▍ | 247/291 [01:03<00:13, 3.29it/s]
Loading 0: 85%|████████▌ | 248/291 [01:04<00:16, 2.61it/s]
Loading 0: 86%|████████▋ | 251/291 [01:04<00:09, 4.44it/s]
Loading 0: 87%|████████▋ | 252/291 [01:04<00:08, 4.68it/s]
Loading 0: 87%|████████▋ | 253/291 [01:04<00:07, 5.26it/s]
Loading 0: 88%|████████▊ | 255/291 [01:05<00:08, 4.39it/s]
Loading 0: 88%|████████▊ | 256/291 [01:06<00:10, 3.32it/s]
Loading 0: 88%|████████▊ | 257/291 [01:06<00:12, 2.63it/s]
Loading 0: 89%|████████▉ | 260/291 [01:06<00:06, 4.45it/s]
Loading 0: 90%|████████▉ | 261/291 [01:07<00:06, 4.68it/s]
Loading 0: 90%|█████████ | 262/291 [01:07<00:05, 5.13it/s]
Loading 0: 91%|█████████ | 264/291 [01:07<00:06, 4.32it/s]
Loading 0: 91%|█████████ | 265/291 [01:08<00:07, 3.28it/s]
Loading 0: 91%|█████████▏| 266/291 [01:08<00:09, 2.61it/s]
Loading 0: 92%|█████████▏| 269/291 [01:09<00:04, 4.49it/s]
Loading 0: 93%|█████████▎| 270/291 [01:09<00:04, 4.72it/s]
Loading 0: 93%|█████████▎| 271/291 [01:09<00:03, 5.28it/s]
Loading 0: 94%|█████████▍| 273/291 [01:09<00:04, 4.38it/s]
Loading 0: 94%|█████████▍| 274/291 [01:10<00:05, 3.30it/s]
Loading 0: 95%|█████████▍| 275/291 [01:11<00:06, 2.62it/s]
Loading 0: 96%|█████████▌| 278/291 [01:11<00:02, 4.50it/s]
Loading 0: 96%|█████████▌| 279/291 [01:11<00:02, 4.74it/s]
Loading 0: 96%|█████████▌| 280/291 [01:11<00:02, 5.33it/s]
Loading 0: 97%|█████████▋| 281/291 [01:12<00:02, 3.55it/s]
Loading 0: 97%|█████████▋| 282/291 [01:12<00:03, 2.65it/s]
Loading 0: 98%|█████████▊| 284/291 [01:13<00:01, 3.81it/s]
Loading 0: 98%|█████████▊| 285/291 [01:13<00:01, 4.16it/s]
Loading 0: 98%|█████████▊| 286/291 [01:13<00:01, 4.82it/s]
Loading 0: 99%|█████████▊| 287/291 [01:13<00:00, 4.95it/s]
Loading 0: 99%|█████████▉| 288/291 [01:14<00:00, 3.28it/s]
Job rirv938-llama-8b-pairwis-6659-v7-mkmlizer completed after 135.41s with status: succeeded
Stopping job with name rirv938-llama-8b-pairwis-6659-v7-mkmlizer
Pipeline stage MKMLizer completed in 135.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-pairwis-6659-v7
Waiting for inference service rirv938-llama-8b-pairwis-6659-v7 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-llama-8b-pairwis-6659-v7 ready after 201.3043315410614s
Pipeline stage MKMLDeployer completed in 201.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4904162883758545s
Received healthy response to inference request in 2.4437096118927s
Received healthy response to inference request in 2.484266757965088s
Received healthy response to inference request in 2.554145574569702s
Received healthy response to inference request in 3.789910078048706s
5 requests
0 failed requests
5th percentile: 2.451821041107178
10th percentile: 2.459932470321655
20th percentile: 2.47615532875061
30th percentile: 2.4982425212860107
40th percentile: 2.5261940479278566
50th percentile: 2.554145574569702
60th percentile: 2.928653860092163
70th percentile: 3.303162145614624
80th percentile: 3.5503150463104247
90th percentile: 3.6701125621795656
95th percentile: 3.730011320114136
99th percentile: 3.777930326461792
mean time: 2.95248966217041
Pipeline stage StressChecker completed in 16.30s
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 2.42s
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 2.25s
Shutdown handler de-registered
rirv938-llama-8b-pairwis_6659_v7 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 0.13s
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-6659-v7-profiler
Waiting for inference service rirv938-llama-8b-pairwis-6659-v7-profiler to be ready
Inference service rirv938-llama-8b-pairwis-6659-v7-profiler ready after 200.46763730049133s
Pipeline stage MKMLProfilerDeployer completed in 200.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs:/code/chaiverse_profiler_1734044810 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734044810 && 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_1734044810/summary.json'
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1734044810/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs:/code/chaiverse_profiler_1734045918 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734045918 && 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_1734045918/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs:/code/chaiverse_profiler_1734046230 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplophlqs --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734046230 && 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_1734046230/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\nTraceback (most recent call last):\n File "/code/chaiverse_profiler_1734046230/profiles.py", line 574, 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_1734046230/profiles.py", line 90, in profile_batches\n client.wait_for_server_startup(target, max_wait=300)\n File "/code/inference_analysis/client.py", line 136, in wait_for_server_startup\n raise RuntimeError(msg)\nRuntimeError: Timed out after 300s waiting for startup\ncommand terminated with exit code 1\n, output: waiting for startup of TargetModel(endpoint=\'localhost\', route=\'GPT-J-6B-lit-v2\', namespace=\'tenant-chaiml-guanaco\', max_characters=9999, reward=False, url_format=\'{endpoint}-predictor-default.{namespace}.knative.ord1.coreweave.cloud\')\n')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-6659-v7-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-6659-v7-profiler
Service rirv938-llama-8b-pairwis-6659-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
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-6659-v7-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.49s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-pairwis-6659-v7-profiler
Waiting for inference service rirv938-llama-8b-pairwis-6659-v7-profiler to be ready
Inference service rirv938-llama-8b-pairwis-6659-v7-profiler ready after 150.38227248191833s
Pipeline stage MKMLProfilerDeployer completed in 150.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplohn7fp:/code/chaiverse_profiler_1734046728 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplohn7fp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734046728 && 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_1734046728/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplohn7fp:/code/chaiverse_profiler_1734049520 --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-pai00c40f27c1be3777693de6909acb05e4-deplohn7fp:/code/chaiverse_profiler_1734049521 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplohn7fp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734049521 && 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_1734049521/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-6659-v7-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-6659-v7-profiler
Service rirv938-llama-8b-pairwis-6659-v7-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-6659-v7-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.25s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-pairwis-6659-v7-profiler
Waiting for inference service rirv938-llama-8b-pairwis-6659-v7-profiler to be ready
Inference service rirv938-llama-8b-pairwis-6659-v7-profiler ready after 70.2365255355835s
Pipeline stage MKMLProfilerDeployer completed in 70.59s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplo5twq6:/code/chaiverse_profiler_1734050271 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplo5twq6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734050271 && 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_1734050271/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplo5twq6:/code/chaiverse_profiler_1734053047 --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-pai00c40f27c1be3777693de6909acb05e4-deplo5twq6:/code/chaiverse_profiler_1734053048 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-pai00c40f27c1be3777693de6909acb05e4-deplo5twq6 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734053048 && 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_1734053048/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-pairwis-6659-v7-profiler is running
Tearing down inference service rirv938-llama-8b-pairwis-6659-v7-profiler
Service rirv938-llama-8b-pairwis-6659-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.29s
Shutdown handler de-registered
rirv938-llama-8b-pairwis_6659_v7 status is now inactive due to auto deactivation removed underperforming models