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-20241009-tie-4134-v1-mkmlizer
Waiting for job on chaiml-nemo-20241009-tie-4134-v1-mkmlizer to finish
Failed to get response for submission nousresearch-meta-llama_4941_v54: ('http://nousresearch-meta-llama-4941-v54-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:58490->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ _____ __ __ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ /___/ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ Version: 0.11.12 ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ belonging to: ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ║ ║
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: Downloaded to shared memory in 49.905s
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7vb3250x, device:0
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: quantized model in 36.110s
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: Processed model ChaiML/nemo-20241009-ties-v6-albert in 86.015s
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1/config.json
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1/special_tokens_map.json
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1/tokenizer_config.json
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1/tokenizer.json
chaiml-nemo-20241009-tie-4134-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-4134-v1/flywheel_model.0.safetensors
Job chaiml-nemo-20241009-tie-4134-v1-mkmlizer completed after 114.14s with status: succeeded
Stopping job with name chaiml-nemo-20241009-tie-4134-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.67s
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 chaiml-nemo-20241009-tie-4134-v1
Waiting for inference service chaiml-nemo-20241009-tie-4134-v1 to be ready
Inference service chaiml-nemo-20241009-tie-4134-v1 ready after 130.46899390220642s
Pipeline stage MKMLDeployer completed in 131.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0929999351501465s
Received healthy response to inference request in 1.5182673931121826s
Received healthy response to inference request in 1.5528547763824463s
Received healthy response to inference request in 1.66206693649292s
Received healthy response to inference request in 1.4028072357177734s
5 requests
0 failed requests
5th percentile: 1.4258992671966553
10th percentile: 1.448991298675537
20th percentile: 1.4951753616333008
30th percentile: 1.5251848697662354
40th percentile: 1.5390198230743408
50th percentile: 1.5528547763824463
60th percentile: 1.5965396404266357
70th percentile: 1.6402245044708252
80th percentile: 1.7482535362243654
90th percentile: 1.920626735687256
95th percentile: 2.006813335418701
99th percentile: 2.0757626152038573
mean time: 1.6457992553710938
Pipeline stage StressChecker completed in 9.76s
Shutdown handler de-registered
chaiml-nemo-20241009-tie_4134_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241009-tie_4134_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241009-tie_4134_v1 status is now torndown due to DeploymentManager action