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-16335-v2-uploader
Waiting for job on chaiml-q235b-opus-judge-16335-v2-uploader to finish
chaiml-q235b-opus-judge-16335-v2-uploader: Using quantization_mode: w4a16
chaiml-q235b-opus-judge-16335-v2-uploader: Checking if ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step210-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-judge-16335-v2-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-q235b-opus-judge-16335-v2-uploader: Downloading snapshot of ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step210-merged-W4A16...
2026-04-02T17:55:59.204590+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
chaiml-q235b-opus-judge-16335-v2-uploader: Downloaded in 56.850s
chaiml-q235b-opus-judge-16335-v2-uploader: Processed model ChaiML/q235b_opus_judge_dpo_with_repetition_fixed-step210-merged in 59.533s
chaiml-q235b-opus-judge-16335-v2-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-16335-v2-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-opus-judge-16335-v2-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-16335-v2-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-16335-v2-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-16335-v2-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-judge-16335-v2-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-q235b-opus-judge-16335-v2-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-q235b-opus-judge-16335-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-q235b-opus-judge-16335-v2-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-q235b-opus-judge-16335-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-q235b-opus-judge-16335-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/chat_template.jinja
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/tokenizer_config.json
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/quantization_config.json
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/config.json
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/generation_config.json
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/.gitattributes
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model.safetensors.index.json
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/tokenizer.json
2026-04-02T17:56:59.299543+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T17:57:59.392732+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00025-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00025-of-00025.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
2026-04-02T17:58:59.484896+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00013-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00013-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00018-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00018-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00002-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00002-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00010-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00010-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00012-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00012-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00008-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00008-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00004-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00004-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00006-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00006-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00001-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00001-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00007-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00007-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00014-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00014-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00015-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00015-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00024-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00024-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00017-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00017-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00003-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00003-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00023-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00023-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00009-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00009-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00005-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00005-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00011-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00011-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00022-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00022-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00020-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00020-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00021-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00021-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00019-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00019-of-00025.safetensors
chaiml-q235b-opus-judge-16335-v2-uploader: cp /dev/shm/model_output/model-00016-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-judge-16335-v2/default/model-00016-of-00025.safetensors
Job chaiml-q235b-opus-judge-16335-v2-uploader completed after 257.33s with status: succeeded
Stopping job with name chaiml-q235b-opus-judge-16335-v2-uploader
Pipeline stage VLLMUploader completed in 258.03s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.11s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.46s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-opus-judge-16335-v2
Waiting for inference service chaiml-q235b-opus-judge-16335-v2 to be ready
2026-04-02T17:59:59.580161+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:00:59.706530+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:02:00.344017+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:03:00.526842+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:04:00.667058+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:05:00.945852+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:06:01.257582+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:07:01.399435+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
Failed to get request counts for guanaco-submitter. Falling back to default
2026-04-02T18:08:01.496393+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:09:01.647012+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
2026-04-02T18:10:01.783183+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
Inference service chaiml-q235b-opus-judge-16335-v2 ready after 693.7917103767395s
Pipeline stage VLLMDeployer completed in 694.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.548844337463379s
Received healthy response to inference request in 1.5951149463653564s
Received healthy response to inference request in 1.470719337463379s
2026-04-02T18:11:01.884128+00:00 monitor updated for chaiml-q235b-opus-judge_16335_v2
Received healthy response to inference request in 1.4378290176391602s
Received healthy response to inference request in 2.0981404781341553s
Received healthy response to inference request in 1.451873540878296s
Received healthy response to inference request in 1.529261589050293s
Received healthy response to inference request in 1.475027322769165s
Received healthy response to inference request in 1.8877036571502686s
Received healthy response to inference request in 1.608231782913208s
Received healthy response to inference request in 1.6790266036987305s
Received healthy response to inference request in 1.5404129028320312s
Received healthy response to inference request in 1.4595611095428467s
Received healthy response to inference request in 1.4839379787445068s
Received healthy response to inference request in 1.9294590950012207s
Received healthy response to inference request in 1.4569649696350098s
Received healthy response to inference request in 1.534294605255127s
Received healthy response to inference request in 1.9990532398223877s
Received healthy response to inference request in 1.5599513053894043s
Received healthy response to inference request in 1.5886304378509521s
Received healthy response to inference request in 1.916332483291626s
Received healthy response to inference request in 1.4313616752624512s
Received healthy response to inference request in 1.6076791286468506s
Received healthy response to inference request in 1.5805373191833496s
Received healthy response to inference request in 1.5076282024383545s
Received healthy response to inference request in 2.181436538696289s
Received healthy response to inference request in 1.4496135711669922s
Received healthy response to inference request in 1.5174047946929932s
Received healthy response to inference request in 1.6041219234466553s
Received healthy response to inference request in 1.465512752532959s
30 requests
0 failed requests
5th percentile: 1.4431320667266845
10th percentile: 1.4516475439071654
20th percentile: 1.4643224239349366
30th percentile: 1.4812647819519043
40th percentile: 1.524518871307373
50th percentile: 1.5501821041107178
60th percentile: 1.591224241256714
70th percentile: 1.607844924926758
80th percentile: 1.8934294223785402
90th percentile: 2.0089619636535647
95th percentile: 2.1439533114433287
99th percentile: 3.152296075820924
mean time: 1.6865222215652467
Pipeline stage StressChecker completed in 53.80s
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 1.66s
Shutdown handler de-registered
chaiml-q235b-opus-judge_16335_v2 status is now deployed due to DeploymentManager action
chaiml-q235b-opus-judge_16335_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-q235b-opus-judge_16335_v2 status is now torndown due to DeploymentManager action