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 chaiml-nemo-20241010-ti-5991-v71-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v71-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ /___/ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ║ ║
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: Downloaded to shared memory in 29.181s
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuk236kpp, device:0
chaiml-nemo-20241010-ti-5991-v71-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission sao10k-mn-12b-lyra-v4a1_v3: ('http://sao10k-mn-12b-lyra-v4a1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56470->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: quantized model in 37.944s
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 67.125s
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71/config.json
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71/tokenizer.json
chaiml-nemo-20241010-ti-5991-v71-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v71/flywheel_model.0.safetensors
Job chaiml-nemo-20241010-ti-5991-v71-mkmlizer completed after 93.93s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v71-mkmlizer
Pipeline stage MKMLizer completed in 94.46s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-ti-5991-v71
Waiting for inference service chaiml-nemo-20241010-ti-5991-v71 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v71 ready after 160.56142950057983s
Pipeline stage MKMLDeployer completed in 161.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.103451728820801s
Received healthy response to inference request in 1.4099390506744385s
Received healthy response to inference request in 1.352508306503296s
Received healthy response to inference request in 1.5249724388122559s
Received healthy response to inference request in 1.417654037475586s
5 requests
0 failed requests
5th percentile: 1.3639944553375245
10th percentile: 1.3754806041717529
20th percentile: 1.3984529018402099
30th percentile: 1.411482048034668
40th percentile: 1.414568042755127
50th percentile: 1.417654037475586
60th percentile: 1.460581398010254
70th percentile: 1.5035087585449218
80th percentile: 1.640668296813965
90th percentile: 1.8720600128173828
95th percentile: 1.9877558708190917
99th percentile: 2.080312557220459
mean time: 1.5617051124572754
Pipeline stage StressChecker completed in 9.22s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v71 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v71 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v71 status is now torndown due to DeploymentManager action