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-q235b-opus-judge-50366-v2-uploader
Waiting for job on chaiml-q235b-opus-judge-50366-v2-uploader to finish
chaiml-q235b-opus-judge-50366-v2-uploader: Using quantization_mode: w4a16
chaiml-q235b-opus-judge-50366-v2-uploader: Checking if ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-judge-50366-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-q235b-opus-judge-50366-v2-uploader: Downloading snapshot of ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged-W4A16...
2026-04-02T17:56:03.375585+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
chaiml-q235b-opus-judge-50366-v2-uploader: Downloaded in 52.644s
chaiml-q235b-opus-judge-50366-v2-uploader: Processed model ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step420-merged in 55.465s
chaiml-q235b-opus-judge-50366-v2-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v2-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-opus-judge-50366-v2-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v2-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v2-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v2-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-50366-v2-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-q235b-opus-judge-50366-v2-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-q235b-opus-judge-50366-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-q235b-opus-judge-50366-v2-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-q235b-opus-judge-50366-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-q235b-opus-judge-50366-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/chat_template.jinja
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/.gitattributes
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/config.json
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/tokenizer_config.json
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/quantization_config.json
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/generation_config.json
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/tokenizer.json
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model.safetensors.index.json
2026-04-02T17:57:03.460709+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00025-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00025-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00022-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00022-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00006-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00006-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00002-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00002-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00021-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00021-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00007-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00007-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00011-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00011-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00016-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00016-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00012-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00012-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00001-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00001-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00024-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00024-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00015-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00015-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00020-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00020-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00019-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00019-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00005-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00005-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00010-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00010-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00008-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00008-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00017-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00017-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00003-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00003-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00014-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00014-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00013-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00013-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00009-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00009-of-00025.safetensors
chaiml-q235b-opus-judge-50366-v2-uploader: cp /dev/shm/model_output/model-00004-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-50366-v2/default/model-00004-of-00025.safetensors
Job chaiml-q235b-opus-judge-50366-v2-uploader completed after 144.42s with status: succeeded
Stopping job with name chaiml-q235b-opus-judge-50366-v2-uploader
Pipeline stage VLLMUploader completed in 144.87s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.13s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 1.41s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-opus-judge-50366-v2
Waiting for inference service chaiml-q235b-opus-judge-50366-v2 to be ready
2026-04-02T17:58:03.542572+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T17:59:03.640099+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:00:03.727533+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:01:03.811482+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:02:03.897505+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:03:03.985841+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:04:04.117384+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:05:04.217493+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:06:04.309150+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:07:04.820479+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:08:04.913080+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:09:05.003358+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:10:05.144689+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:11:05.271835+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:12:05.380957+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:13:05.963547+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:14:06.127357+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:15:06.320135+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:16:06.869665+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:17:06.963433+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:18:07.057882+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:19:07.163908+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:20:07.259708+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:21:07.361992+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:22:07.484101+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:23:07.783795+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
2026-04-02T18:24:07.883196+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
Inference service chaiml-q235b-opus-judge-50366-v2 ready after 1616.8559548854828s
Pipeline stage VLLMDeployer completed in 1617.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.501030921936035s
Received healthy response to inference request in 1.4919161796569824s
Received healthy response to inference request in 1.4776670932769775s
Received healthy response to inference request in 1.545473337173462s
Received healthy response to inference request in 1.672553539276123s
Received healthy response to inference request in 1.935046911239624s
Received healthy response to inference request in 1.6733431816101074s
Received healthy response to inference request in 1.627152442932129s
Received healthy response to inference request in 1.571767807006836s
Received healthy response to inference request in 1.6266112327575684s
Received healthy response to inference request in 1.5305707454681396s
Received healthy response to inference request in 1.4703776836395264s
Received healthy response to inference request in 1.4522020816802979s
Received healthy response to inference request in 1.7592616081237793s
Received healthy response to inference request in 1.8370153903961182s
Received healthy response to inference request in 1.4549281597137451s
Received healthy response to inference request in 1.6335771083831787s
Received healthy response to inference request in 1.498016595840454s
Received healthy response to inference request in 1.9374122619628906s
Received healthy response to inference request in 1.7812402248382568s
Received healthy response to inference request in 2.1532340049743652s
Received healthy response to inference request in 1.476881742477417s
2026-04-02T18:25:07.992448+00:00 monitor updated for chaiml-q235b-opus-judge_50366_v2
Received healthy response to inference request in 1.8716392517089844s
Received healthy response to inference request in 1.5543406009674072s
Received healthy response to inference request in 1.720106840133667s
Received healthy response to inference request in 2.2199487686157227s
Received healthy response to inference request in 1.4992437362670898s
Received healthy response to inference request in 1.805509328842163s
Received healthy response to inference request in 1.6154873371124268s
Received healthy response to inference request in 1.7041711807250977s
30 requests
0 failed requests
5th percentile: 1.4618804454803467
10th percentile: 1.476231336593628
20th percentile: 1.4967965126037597
30th percentile: 1.5410025596618653
40th percentile: 1.5979995250701904
50th percentile: 1.6303647756576538
60th percentile: 1.6856743812561035
70th percentile: 1.7658551931381226
80th percentile: 1.8439401626586915
90th percentile: 1.9589944362640384
95th percentile: 2.1899271249771117
99th percentile: 3.1295170974731454
mean time: 1.7365909099578858
Pipeline stage StressChecker completed in 56.28s
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 0.72s
Shutdown handler de-registered
chaiml-q235b-opus-judge_50366_v2 status is now deployed due to DeploymentManager action
chaiml-q235b-opus-judge_50366_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-q235b-opus-judge_50366_v2 status is now torndown due to DeploymentManager action