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 sao10k-mn-12b-lyra-v4a1-v12-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a1-v12-mkmlizer to finish
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ _____ __ __ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ /___/ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ Version: 0.11.12 ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ https://mk1.ai ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ belonging to: ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ Chai Research Corp. ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ║ ║
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: Downloaded to shared memory in 34.423s
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqewgq3pk, device:0
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: quantized model in 37.114s
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: Processed model Sao10K/MN-12B-Lyra-v4a1 in 71.537s
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v12
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v12/config.json
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v12/special_tokens_map.json
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v12/tokenizer_config.json
sao10k-mn-12b-lyra-v4a1-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a1-v12/tokenizer.json
Job sao10k-mn-12b-lyra-v4a1-v12-mkmlizer completed after 120.06s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a1-v12-mkmlizer
Pipeline stage MKMLizer completed in 120.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v4a1-v12
Waiting for inference service sao10k-mn-12b-lyra-v4a1-v12 to be ready
Inference service sao10k-mn-12b-lyra-v4a1-v12 ready after 120.74027991294861s
Pipeline stage MKMLDeployer completed in 121.29s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8903186321258545s
Received healthy response to inference request in 1.3591444492340088s
Received healthy response to inference request in 1.5458946228027344s
Received healthy response to inference request in 1.5148310661315918s
Received healthy response to inference request in 1.8090214729309082s
5 requests
0 failed requests
5th percentile: 1.3902817726135255
10th percentile: 1.421419095993042
20th percentile: 1.483693742752075
30th percentile: 1.5210437774658203
40th percentile: 1.5334692001342773
50th percentile: 1.5458946228027344
60th percentile: 1.6511453628540038
70th percentile: 1.7563961029052735
80th percentile: 1.8252809047698975
90th percentile: 1.857799768447876
95th percentile: 1.8740592002868652
99th percentile: 1.8870667457580566
mean time: 1.6238420486450196
Pipeline stage StressChecker completed in 9.39s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a1_v12 status is now deployed due to DeploymentManager action
sao10k-mn-12b-lyra-v4a1_v12 status is now inactive due to auto deactivation removed underperforming models
sao10k-mn-12b-lyra-v4a1_v12 status is now deployed due to admin request
sao10k-mn-12b-lyra-v4a1_v12 status is now inactive due to auto deactivation removed underperforming models