Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-bol-v1-opusdv1b-13427-v8-uploader
Waiting for job on chaiml-bol-v1-opusdv1b-13427-v8-uploader to finish
chaiml-bol-v1-opusdv1b-13427-v8-uploader: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-bol-v1-opusdv1b-13427-v8-uploader: bash: no job control in this shell
chaiml-bol-v1-opusdv1b-13427-v8-uploader: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-bol-v1-opusdv1b-13427-v8-uploader: __import__('pkg_resources').declare_namespace(__name__)
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ██████ ██████ █████ ████ ████ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ █████ █████ █████ ░░████ █████ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Version: 0.30.6+torch280 ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Features: FLYWHEEL, CUDA ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ https://mk1.ai ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ The license key for the current software has been verified as ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ belonging to: ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Chai Research Corp. ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ║ ║
chaiml-bol-v1-opusdv1b-13427-v8-uploader: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-bol-v1-opusdv1b-13427-v8-uploader: Downloaded to shared memory in 116.874s
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
chaiml-bol-v1-opusdv1b-13427-v8-uploader: Processed model ChaiML/bol-v1-opusdv1b-lr5e6ep2r64g4b01-int4-mixed in 182.173s
chaiml-bol-v1-opusdv1b-13427-v8-uploader: creating bucket guanaco-vllm-models
chaiml-bol-v1-opusdv1b-13427-v8-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-bol-v1-opusdv1b-13427-v8-uploader: uploading /dev/shm/model_cache to s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/added_tokens.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/chat_template.jinja s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/chat_template.jinja
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/.gitattributes s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/.gitattributes
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/tokenizer_config.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/generation_config.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/generation_config.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/special_tokens_map.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/config.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/config.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/quantization_config.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/quantization_config.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/tokenizer.json
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/vocab.json s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/vocab.json
HTTP Request: %s %s "%s %d %s"
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00027-of-00027.safetensors
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00008-of-00027.safetensors
HTTP Request: %s %s "%s %d %s"
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00017-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00017-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00009-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00015-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00003-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00010-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00025-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00022-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00018-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00001-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00012-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00007-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00016-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00023-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00002-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00019-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00026-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00014-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00005-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00024-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00006-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00021-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00004-of-00027.safetensors
chaiml-bol-v1-opusdv1b-13427-v8-uploader: cp /dev/shm/model_cache/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-bol-v1-opusdv1b-13427-v8/model-00013-of-00027.safetensors
HTTP Request: %s %s "%s %d %s"
Job chaiml-bol-v1-opusdv1b-13427-v8-uploader completed after 642.7s with status: succeeded
Stopping job with name chaiml-bol-v1-opusdv1b-13427-v8-uploader
Pipeline stage VLLMUploader completed in 643.06s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-bol-v1-opusdv1b-13427-v8
Waiting for inference service chaiml-bol-v1-opusdv1b-13427-v8 to be ready
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-bol-v1-opusdv1b-13427-v8 ready after 440.29869627952576s
Pipeline stage VLLMDeployer completed in 440.68s
run pipeline stage %s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.8799481391906738s
Received healthy response to inference request in 1.8938918113708496s
Received healthy response to inference request in 1.8538084030151367s
Received healthy response to inference request in 2.1582448482513428s
Received healthy response to inference request in 2.4474472999572754s
Received healthy response to inference request in 2.3151044845581055s
Received healthy response to inference request in 2.6369242668151855s
Received healthy response to inference request in 1.7585511207580566s
Received healthy response to inference request in 2.0898914337158203s
Received healthy response to inference request in 1.9448893070220947s
Received healthy response to inference request in 2.3252692222595215s
Received healthy response to inference request in 1.7639470100402832s
Received healthy response to inference request in 2.4226365089416504s
Received healthy response to inference request in 2.2716195583343506s
Received healthy response to inference request in 2.0883612632751465s
Received healthy response to inference request in 1.7699995040893555s
Received healthy response to inference request in 1.7398130893707275s
Received healthy response to inference request in 2.1592934131622314s
Received healthy response to inference request in 1.7780756950378418s
Received healthy response to inference request in 2.0981178283691406s
Received healthy response to inference request in 1.7760753631591797s
Received healthy response to inference request in 1.7413229942321777s
Received healthy response to inference request in 2.34334135055542s
Received healthy response to inference request in 2.063246250152588s
Received healthy response to inference request in 1.8174717426300049s
Received healthy response to inference request in 1.763141393661499s
Received healthy response to inference request in 2.056898832321167s
Received healthy response to inference request in 2.2425131797790527s
Received healthy response to inference request in 1.7693147659301758s
30 requests
1 failed requests
5th percentile: 1.7490756511688232
10th percentile: 1.7626823663711548
20th percentile: 1.7698625564575194
30th percentile: 1.805652928352356
40th percentile: 1.8883143424987794
50th percentile: 2.0600725412368774
60th percentile: 2.0931819915771483
70th percentile: 2.1842593431472777
80th percentile: 2.317137432098389
90th percentile: 2.425117588043213
95th percentile: 2.5516596317291254
99th percentile: 15.066409096717848
mean time: 2.6370800336201987
%s, retrying in %s seconds...
Received healthy response to inference request in 2.053954839706421s
Received healthy response to inference request in 1.741899013519287s
Received healthy response to inference request in 2.1548943519592285s
Received healthy response to inference request in 2.6489744186401367s
Received healthy response to inference request in 1.7954483032226562s
Received healthy response to inference request in 1.741396188735962s
Received healthy response to inference request in 2.1073930263519287s
Received healthy response to inference request in 1.7312936782836914s
Received healthy response to inference request in 2.6050806045532227s
Received healthy response to inference request in 2.1015403270721436s
Received healthy response to inference request in 1.7643897533416748s
Received healthy response to inference request in 1.7523815631866455s
Received healthy response to inference request in 1.7451157569885254s
Received healthy response to inference request in 2.4655892848968506s
Received healthy response to inference request in 1.6948554515838623s
Received healthy response to inference request in 1.820587396621704s
Received healthy response to inference request in 2.27054762840271s
Received healthy response to inference request in 1.7455613613128662s
Received healthy response to inference request in 1.7542340755462646s
Received healthy response to inference request in 2.2368457317352295s
Received healthy response to inference request in 2.0353312492370605s
Received healthy response to inference request in 2.095292568206787s
Received healthy response to inference request in 2.5965216159820557s
Received healthy response to inference request in 1.8470845222473145s
Received healthy response to inference request in 2.4076011180877686s
Received healthy response to inference request in 2.5359082221984863s
Received healthy response to inference request in 1.9468698501586914s
Received healthy response to inference request in 1.933462142944336s
Received healthy response to inference request in 2.134739637374878s
Received healthy response to inference request in 2.2424957752227783s
30 requests
0 failed requests
5th percentile: 1.735839807987213
10th percentile: 1.7418487310409545
20th percentile: 1.7510175228118896
30th percentile: 1.7861307382583618
40th percentile: 1.8989110946655274
50th percentile: 2.0446430444717407
60th percentile: 2.1038814067840574
70th percentile: 2.1794797658920286
80th percentile: 2.297958326339722
90th percentile: 2.541969561576843
95th percentile: 2.6012290596961973
99th percentile: 2.6362452125549316
mean time: 2.0569096485773724
Pipeline stage StressChecker completed in 147.37s
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 0.62s
Shutdown handler de-registered
chaiml-bol-v1-opusdv1b-_13427_v8 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 5347.23s
Shutdown handler de-registered
chaiml-bol-v1-opusdv1b-_13427_v8 status is now torndown due to DeploymentManager action