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-400k-12-1094-v1-mkmlizer
Waiting for job on rirv938-llama-8b-400k-12-1094-v1-mkmlizer to finish
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ /___/ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ║ ║
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: Downloaded to shared memory in 38.584s
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp_2f06ive, device:0
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: quantized model in 85.777s
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: Processed model rirv938/llama_8b_400k_128_tokens in 124.362s
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1/config.json
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1/special_tokens_map.json
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1/tokenizer_config.json
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1/tokenizer.json
rirv938-llama-8b-400k-12-1094-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-400k-12-1094-v1/flywheel_model.0.safetensors
rirv938-llama-8b-400k-12-1094-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%| | 3/291 [00:00<00:56, 5.08it/s]
Loading 0: 1%|▏ | 4/291 [00:01<01:32, 3.10it/s]
Loading 0: 2%|▏ | 5/291 [00:01<02:04, 2.30it/s]
Loading 0: 3%|▎ | 8/291 [00:02<01:04, 4.40it/s]
Loading 0: 3%|▎ | 9/291 [00:02<01:03, 4.46it/s]
Loading 0: 3%|▎ | 10/291 [00:02<00:55, 5.08it/s]
Loading 0: 4%|▍ | 12/291 [00:02<01:05, 4.26it/s]
Loading 0: 4%|▍ | 13/291 [00:03<01:27, 3.19it/s]
Loading 0: 5%|▍ | 14/291 [00:04<01:49, 2.54it/s]
Loading 0: 6%|▌ | 17/291 [00:04<01:03, 4.33it/s]
Loading 0: 6%|▌ | 18/291 [00:04<00:59, 4.55it/s]
Loading 0: 7%|▋ | 19/291 [00:04<00:53, 5.12it/s]
Loading 0: 7%|▋ | 21/291 [00:05<01:02, 4.30it/s]
Loading 0: 8%|▊ | 22/291 [00:05<01:23, 3.24it/s]
Loading 0: 8%|▊ | 23/291 [00:06<01:45, 2.53it/s]
Loading 0: 9%|▉ | 26/291 [00:06<01:02, 4.21it/s]
Loading 0: 9%|▉ | 27/291 [00:06<00:59, 4.43it/s]
Loading 0: 10%|▉ | 28/291 [00:07<00:53, 4.93it/s]
Loading 0: 10%|█ | 30/291 [00:07<01:01, 4.22it/s]
Loading 0: 11%|█ | 31/291 [00:08<01:20, 3.21it/s]
Loading 0: 11%|█ | 32/291 [00:08<01:42, 2.53it/s]
Loading 0: 12%|█▏ | 35/291 [00:09<00:59, 4.31it/s]
Loading 0: 12%|█▏ | 36/291 [00:09<00:56, 4.55it/s]
Loading 0: 13%|█▎ | 38/291 [00:09<00:40, 6.27it/s]
Loading 0: 14%|█▎ | 40/291 [00:10<01:15, 3.32it/s]
Loading 0: 14%|█▍ | 41/291 [00:11<01:32, 2.71it/s]
Loading 0: 15%|█▌ | 44/291 [00:11<00:57, 4.29it/s]
Loading 0: 15%|█▌ | 45/291 [00:11<00:54, 4.52it/s]
Loading 0: 16%|█▌ | 46/291 [00:11<00:48, 5.04it/s]
Loading 0: 16%|█▋ | 48/291 [00:12<00:56, 4.32it/s]
Loading 0: 17%|█▋ | 49/291 [00:12<01:13, 3.29it/s]
Loading 0: 17%|█▋ | 50/291 [00:13<01:33, 2.59it/s]
Loading 0: 18%|█▊ | 53/291 [00:13<00:53, 4.41it/s]
Loading 0: 19%|█▊ | 54/291 [00:13<00:51, 4.63it/s]
Loading 0: 19%|█▉ | 55/291 [00:13<00:45, 5.23it/s]
Loading 0: 20%|█▉ | 57/291 [00:14<00:53, 4.37it/s]
Loading 0: 20%|█▉ | 58/291 [00:15<01:11, 3.28it/s]
Loading 0: 20%|██ | 59/291 [00:15<01:29, 2.59it/s]
Loading 0: 21%|██▏ | 62/291 [00:16<00:51, 4.45it/s]
Loading 0: 22%|██▏ | 63/291 [00:16<00:47, 4.75it/s]
Loading 0: 23%|██▎ | 66/291 [00:16<00:49, 4.59it/s]
Loading 0: 23%|██▎ | 67/291 [00:17<01:02, 3.56it/s]
Loading 0: 23%|██▎ | 68/291 [00:18<01:19, 2.80it/s]
Loading 0: 24%|██▍ | 71/291 [00:18<00:48, 4.52it/s]
Loading 0: 25%|██▍ | 72/291 [00:18<00:46, 4.73it/s]
Loading 0: 25%|██▌ | 73/291 [00:18<00:41, 5.25it/s]
Loading 0: 26%|██▌ | 75/291 [00:19<00:49, 4.38it/s]
Loading 0: 26%|██▌ | 76/291 [00:19<01:04, 3.31it/s]
Loading 0: 26%|██▋ | 77/291 [00:20<01:21, 2.63it/s]
Loading 0: 27%|██▋ | 80/291 [00:20<00:47, 4.43it/s]
Loading 0: 28%|██▊ | 81/291 [00:20<00:44, 4.67it/s]
Loading 0: 28%|██▊ | 82/291 [00:20<00:39, 5.24it/s]
Loading 0: 29%|██▊ | 83/291 [00:21<00:39, 5.27it/s]
Loading 0: 29%|██▉ | 84/291 [00:21<00:59, 3.47it/s]
Loading 0: 29%|██▉ | 85/291 [00:22<01:15, 2.74it/s]
Loading 0: 30%|██▉ | 86/291 [00:22<01:30, 2.28it/s]
Loading 0: 31%|███ | 89/291 [00:22<00:47, 4.23it/s]
Loading 0: 31%|███ | 90/291 [00:23<00:44, 4.50it/s]
Loading 0: 31%|███▏ | 91/291 [00:23<00:39, 5.09it/s]
Loading 0: 32%|███▏ | 93/291 [00:23<00:46, 4.30it/s]
Loading 0: 32%|███▏ | 94/291 [00:24<01:00, 3.25it/s]
Loading 0: 33%|███▎ | 95/291 [00:25<01:15, 2.59it/s]
Loading 0: 34%|███▎ | 98/291 [00:25<00:43, 4.41it/s]
Loading 0: 34%|███▍ | 99/291 [00:25<00:41, 4.64it/s]
Loading 0: 34%|███▍ | 100/291 [00:25<00:36, 5.23it/s]
Loading 0: 35%|███▌ | 102/291 [00:26<00:43, 4.35it/s]
Loading 0: 35%|███▌ | 103/291 [00:26<00:57, 3.29it/s]
Loading 0: 36%|███▌ | 104/291 [00:27<01:11, 2.60it/s]
Loading 0: 37%|███▋ | 107/291 [00:27<00:41, 4.40it/s]
Loading 0: 37%|███▋ | 108/291 [00:27<00:39, 4.64it/s]
Loading 0: 37%|███▋ | 109/291 [00:27<00:35, 5.18it/s]
Loading 0: 38%|███▊ | 111/291 [00:28<00:41, 4.35it/s]
Loading 0: 38%|███▊ | 112/291 [00:29<00:54, 3.27it/s]
Loading 0: 39%|███▉ | 113/291 [00:29<01:09, 2.58it/s]
Loading 0: 40%|███▉ | 116/291 [00:29<00:39, 4.38it/s]
Loading 0: 40%|████ | 117/291 [00:30<00:37, 4.62it/s]
Loading 0: 41%|████ | 118/291 [00:30<00:33, 5.22it/s]
Loading 0: 41%|████ | 120/291 [00:30<00:39, 4.37it/s]
Loading 0: 42%|████▏ | 121/291 [00:31<00:51, 3.29it/s]
Loading 0: 42%|████▏ | 122/291 [00:31<01:05, 2.59it/s]
Loading 0: 43%|████▎ | 125/291 [00:32<00:37, 4.44it/s]
Loading 0: 43%|████▎ | 126/291 [00:32<00:35, 4.67it/s]
Loading 0: 44%|████▎ | 127/291 [00:32<00:31, 5.27it/s]
Loading 0: 44%|████▍ | 129/291 [00:33<00:37, 4.38it/s]
Loading 0: 45%|████▍ | 130/291 [00:33<00:48, 3.30it/s]
Loading 0: 45%|████▌ | 131/291 [00:34<01:01, 2.61it/s]
Loading 0: 46%|████▌ | 134/291 [00:34<00:35, 4.43it/s]
Loading 0: 46%|████▋ | 135/291 [00:34<00:32, 4.74it/s]
Loading 0: 47%|████▋ | 138/291 [00:35<00:33, 4.58it/s]
Loading 0: 48%|████▊ | 139/291 [00:35<00:42, 3.54it/s]
Loading 0: 48%|████▊ | 140/291 [00:36<00:53, 2.82it/s]
Loading 0: 49%|████▉ | 143/291 [00:36<00:32, 4.49it/s]
Loading 0: 49%|████▉ | 144/291 [00:36<00:31, 4.71it/s]
Loading 0: 50%|████▉ | 145/291 [00:36<00:27, 5.28it/s]
Loading 0: 51%|█████ | 147/291 [00:37<00:32, 4.41it/s]
Loading 0: 51%|█████ | 148/291 [00:38<00:43, 3.32it/s]
Loading 0: 51%|█████ | 149/291 [00:38<00:54, 2.60it/s]
Loading 0: 52%|█████▏ | 152/291 [00:38<00:31, 4.37it/s]
Loading 0: 53%|█████▎ | 153/291 [00:39<00:29, 4.61it/s]
Loading 0: 53%|█████▎ | 154/291 [00:39<00:26, 5.21it/s]
Loading 0: 54%|█████▎ | 156/291 [00:39<00:30, 4.37it/s]
Loading 0: 54%|█████▍ | 157/291 [00:40<00:40, 3.29it/s]
Loading 0: 54%|█████▍ | 158/291 [00:41<00:51, 2.60it/s]
Loading 0: 55%|█████▌ | 161/291 [00:41<00:29, 4.41it/s]
Loading 0: 56%|█████▌ | 162/291 [00:41<00:27, 4.65it/s]
Loading 0: 56%|█████▋ | 164/291 [00:41<00:19, 6.39it/s]
Loading 0: 57%|█████▋ | 166/291 [00:42<00:37, 3.35it/s]
Loading 0: 57%|█████▋ | 167/291 [00:43<00:45, 2.73it/s]
Loading 0: 58%|█████▊ | 170/291 [00:43<00:28, 4.31it/s]
Loading 0: 59%|█████▉ | 171/291 [00:43<00:26, 4.53it/s]
Loading 0: 59%|█████▉ | 172/291 [00:43<00:23, 5.07it/s]
Loading 0: 59%|█████▉ | 173/291 [00:44<00:33, 3.54it/s]
Loading 0: 60%|██████ | 175/291 [00:44<00:24, 4.79it/s]
Loading 0: 60%|██████ | 176/291 [00:44<00:22, 5.00it/s]
Loading 0: 61%|██████ | 177/291 [00:44<00:20, 5.54it/s]
Loading 0: 62%|██████▏ | 179/291 [00:45<00:25, 4.47it/s]
Loading 0: 62%|██████▏ | 180/291 [00:46<00:33, 3.31it/s]
Loading 0: 62%|██████▏ | 181/291 [00:46<00:42, 2.60it/s]
Loading 0: 63%|██████▎ | 184/291 [00:46<00:23, 4.55it/s]
Loading 0: 64%|██████▎ | 185/291 [00:47<00:22, 4.77it/s]
Loading 0: 64%|██████▍ | 186/291 [00:47<00:19, 5.30it/s]
Loading 0: 64%|██████▍ | 187/291 [00:47<00:19, 5.29it/s]
Loading 0: 65%|██████▍ | 188/291 [00:47<00:29, 3.48it/s]
Loading 0: 65%|██████▍ | 189/291 [00:48<00:38, 2.63it/s]
Loading 0: 66%|██████▌ | 192/291 [00:49<00:27, 3.57it/s]
Loading 0: 66%|██████▋ | 193/291 [00:49<00:33, 2.94it/s]
Loading 0: 67%|██████▋ | 194/291 [00:50<00:39, 2.45it/s]
Loading 0: 68%|██████▊ | 197/291 [00:50<00:22, 4.14it/s]
Loading 0: 68%|██████▊ | 198/291 [00:50<00:21, 4.38it/s]
Loading 0: 68%|██████▊ | 199/291 [00:50<00:18, 4.96it/s]
Loading 0: 69%|██████▉ | 201/291 [00:51<00:21, 4.27it/s]
Loading 0: 69%|██████▉ | 202/291 [00:51<00:27, 3.24it/s]
Loading 0: 70%|██████▉ | 203/291 [00:52<00:34, 2.58it/s]
Loading 0: 71%|███████ | 206/291 [00:52<00:19, 4.38it/s]
Loading 0: 71%|███████ | 207/291 [00:53<00:18, 4.62it/s]
Loading 0: 71%|███████▏ | 208/291 [00:53<00:15, 5.22it/s]
Loading 0: 72%|███████▏ | 210/291 [00:53<00:18, 4.36it/s]
Loading 0: 73%|███████▎ | 211/291 [00:54<00:24, 3.29it/s]
Loading 0: 73%|███████▎ | 212/291 [00:54<00:30, 2.60it/s]
Loading 0: 74%|███████▍ | 215/291 [00:55<00:17, 4.46it/s]
Loading 0: 74%|███████▍ | 216/291 [00:55<00:15, 4.76it/s]
Loading 0: 75%|███████▌ | 219/291 [00:55<00:15, 4.62it/s]
Loading 0: 76%|███████▌ | 220/291 [00:56<00:19, 3.57it/s]
Loading 0: 76%|███████▌ | 221/291 [00:57<00:24, 2.83it/s]
Loading 0: 77%|███████▋ | 224/291 [00:57<00:14, 4.52it/s]
Loading 0: 77%|███████▋ | 225/291 [00:57<00:13, 4.73it/s]
Loading 0: 78%|███████▊ | 226/291 [00:57<00:12, 5.22it/s]
Loading 0: 78%|███████▊ | 228/291 [00:58<00:14, 4.37it/s]
Loading 0: 79%|███████▊ | 229/291 [00:58<00:18, 3.32it/s]
Loading 0: 79%|███████▉ | 230/291 [00:59<00:23, 2.64it/s]
Loading 0: 80%|████████ | 233/291 [00:59<00:12, 4.48it/s]
Loading 0: 80%|████████ | 234/291 [00:59<00:12, 4.72it/s]
Loading 0: 81%|████████ | 235/291 [00:59<00:10, 5.29it/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 [01:01<00:19, 2.63it/s]
Loading 0: 83%|████████▎ | 242/291 [01:01<00:10, 4.52it/s]
Loading 0: 84%|████████▎ | 243/291 [01:02<00:10, 4.74it/s]
Loading 0: 84%|████████▍ | 245/291 [01:02<00:07, 6.49it/s]
Loading 0: 85%|████████▍ | 247/291 [01:03<00:13, 3.38it/s]
Loading 0: 85%|████████▌ | 248/291 [01:03<00:15, 2.76it/s]
Loading 0: 86%|████████▋ | 251/291 [01:04<00:09, 4.36it/s]
Loading 0: 87%|████████▋ | 252/291 [01:04<00:08, 4.59it/s]
Loading 0: 87%|████████▋ | 253/291 [01:04<00:07, 5.14it/s]
Loading 0: 88%|████████▊ | 255/291 [01:04<00:08, 4.37it/s]
Loading 0: 88%|████████▊ | 256/291 [01:05<00:10, 3.33it/s]
Loading 0: 88%|████████▊ | 257/291 [01:06<00:12, 2.65it/s]
Loading 0: 89%|████████▉ | 260/291 [01:06<00:06, 4.52it/s]
Loading 0: 90%|████████▉ | 261/291 [01:06<00:06, 4.74it/s]
Loading 0: 90%|█████████ | 262/291 [01:06<00:05, 5.33it/s]
Loading 0: 91%|█████████ | 264/291 [01:07<00:06, 4.43it/s]
Loading 0: 91%|█████████ | 265/291 [01:07<00:07, 3.34it/s]
Loading 0: 91%|█████████▏| 266/291 [01:08<00:09, 2.64it/s]
Loading 0: 92%|█████████▏| 269/291 [01:08<00:04, 4.53it/s]
Loading 0: 93%|█████████▎| 270/291 [01:08<00:04, 4.76it/s]
Loading 0: 93%|█████████▎| 271/291 [01:08<00:03, 5.28it/s]
Loading 0: 94%|█████████▍| 273/291 [01:09<00:04, 4.39it/s]
Loading 0: 94%|█████████▍| 274/291 [01:10<00:05, 3.32it/s]
Loading 0: 95%|█████████▍| 275/291 [01:10<00:06, 2.61it/s]
Loading 0: 96%|█████████▌| 278/291 [01:10<00:02, 4.48it/s]
Loading 0: 96%|█████████▌| 279/291 [01:11<00:02, 4.71it/s]
Loading 0: 96%|█████████▌| 280/291 [01:11<00:02, 5.31it/s]
Loading 0: 97%|█████████▋| 281/291 [01:11<00:02, 3.56it/s]
Loading 0: 97%|█████████▋| 282/291 [01:12<00:03, 2.68it/s]
Loading 0: 98%|█████████▊| 284/291 [01:12<00:01, 3.86it/s]
Loading 0: 98%|█████████▊| 285/291 [01:12<00:01, 4.21it/s]
Loading 0: 98%|█████████▊| 286/291 [01:12<00:01, 4.89it/s]
Loading 0: 99%|█████████▊| 287/291 [01:13<00:00, 5.12it/s]
Loading 0: 99%|█████████▉| 288/291 [01:13<00:00, 3.33it/s]
Job rirv938-llama-8b-400k-12-1094-v1-mkmlizer completed after 155.67s with status: succeeded
Stopping job with name rirv938-llama-8b-400k-12-1094-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.19s
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 rirv938-llama-8b-400k-12-1094-v1
Waiting for inference service rirv938-llama-8b-400k-12-1094-v1 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
Inference service rirv938-llama-8b-400k-12-1094-v1 ready after 200.99361729621887s
Pipeline stage MKMLDeployer completed in 201.54s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.6820104122161865s
Received healthy response to inference request in 2.8534414768218994s
Received healthy response to inference request in 2.825944662094116s
Received healthy response to inference request in 4.3200976848602295s
Received healthy response to inference request in 3.4522197246551514s
5 requests
0 failed requests
5th percentile: 2.831444025039673
10th percentile: 2.8369433879852295
20th percentile: 2.8479421138763428
30th percentile: 2.9731971263885497
40th percentile: 3.2127084255218508
50th percentile: 3.4522197246551514
60th percentile: 3.7993709087371825
70th percentile: 4.146522092819214
80th percentile: 4.3924802303314205
90th percentile: 4.5372453212738035
95th percentile: 4.6096278667449955
99th percentile: 4.6675339031219485
mean time: 3.626742792129517
%s, retrying in %s seconds...
Received healthy response to inference request in 4.099292755126953s
Received healthy response to inference request in 4.002933025360107s
Received healthy response to inference request in 4.427126169204712s
Received healthy response to inference request in 2.2021286487579346s
Received healthy response to inference request in 4.477261304855347s
5 requests
0 failed requests
5th percentile: 2.562289524078369
10th percentile: 2.922450399398804
20th percentile: 3.642772150039673
30th percentile: 4.022204971313476
40th percentile: 4.060748863220215
50th percentile: 4.099292755126953
60th percentile: 4.2304261207580565
70th percentile: 4.36155948638916
80th percentile: 4.4371531963348385
90th percentile: 4.457207250595093
95th percentile: 4.46723427772522
99th percentile: 4.475255899429321
mean time: 3.8417483806610107
%s, retrying in %s seconds...
Received healthy response to inference request in 3.6285626888275146s
Received healthy response to inference request in 3.62030291557312s
Received healthy response to inference request in 4.281518220901489s
Received healthy response to inference request in 2.3078012466430664s
Received healthy response to inference request in 3.272836923599243s
5 requests
0 failed requests
5th percentile: 2.5008083820343017
10th percentile: 2.693815517425537
20th percentile: 3.079829788208008
30th percentile: 3.3423301219940185
40th percentile: 3.4813165187835695
50th percentile: 3.62030291557312
60th percentile: 3.623606824874878
70th percentile: 3.6269107341766356
80th percentile: 3.7591537952423097
90th percentile: 4.020336008071899
95th percentile: 4.150927114486694
99th percentile: 4.25539999961853
mean time: 3.4222043991088866
Pipeline stage StressChecker completed in 59.10s
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 2.17s
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 2.18s
Shutdown handler de-registered
rirv938-llama-8b-400k-12_1094_v1 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-400k-12-1094-v1-profiler
Waiting for inference service rirv938-llama-8b-400k-12-1094-v1-profiler to be ready
Inference service rirv938-llama-8b-400k-12-1094-v1-profiler ready after 200.4468538761139s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplolv5lv:/code/chaiverse_profiler_1734107768 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplolv5lv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734107768 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734107768/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplolv5lv:/code/chaiverse_profiler_1734110567 --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-400f6dc22a8a64f9c2de25e0e924537ba1d-deplolv5lv:/code/chaiverse_profiler_1734110568 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplolv5lv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734110568 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734110568/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-400k-12-1094-v1-profiler is running
Tearing down inference service rirv938-llama-8b-400k-12-1094-v1-profiler
Service rirv938-llama-8b-400k-12-1094-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.29s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-400k-12-1094-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-400k-12-1094-v1-profiler
Waiting for inference service rirv938-llama-8b-400k-12-1094-v1-profiler to be ready
Inference service rirv938-llama-8b-400k-12-1094-v1-profiler ready after 170.42313504219055s
Pipeline stage MKMLProfilerDeployer completed in 170.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplos58f4:/code/chaiverse_profiler_1734111358 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplos58f4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734111358 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734111358/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplos58f4:/code/chaiverse_profiler_1734114143 --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-400f6dc22a8a64f9c2de25e0e924537ba1d-deplos58f4:/code/chaiverse_profiler_1734114144 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplos58f4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734114144 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734114144/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-400k-12-1094-v1-profiler is running
Tearing down inference service rirv938-llama-8b-400k-12-1094-v1-profiler
Service rirv938-llama-8b-400k-12-1094-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.37s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-400k-12-1094-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.43s
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-400k-12-1094-v1-profiler
Waiting for inference service rirv938-llama-8b-400k-12-1094-v1-profiler to be ready
Inference service rirv938-llama-8b-400k-12-1094-v1-profiler ready after 130.30421376228333s
Pipeline stage MKMLProfilerDeployer completed in 130.64s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplo2b6vg:/code/chaiverse_profiler_1734114945 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplo2b6vg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734114945 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734114945/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplo2b6vg:/code/chaiverse_profiler_1734117743 --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-400f6dc22a8a64f9c2de25e0e924537ba1d-deplo2b6vg:/code/chaiverse_profiler_1734117743 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-400f6dc22a8a64f9c2de25e0e924537ba1d-deplo2b6vg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1734117743 && 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 128 --output_tokens 1 --summary /code/chaiverse_profiler_1734117743/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-400k-12-1094-v1-profiler is running
Tearing down inference service rirv938-llama-8b-400k-12-1094-v1-profiler
Service rirv938-llama-8b-400k-12-1094-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.37s
Shutdown handler de-registered
rirv938-llama-8b-400k-12_1094_v1 status is now inactive due to auto deactivation removed underperforming models