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-pony-v3a-g47-lr1-18022-v4-uploader
Waiting for job on chaiml-pony-v3a-g47-lr1-18022-v4-uploader to finish
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Using quantization_mode: w4a16
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Checking if ChaiML/pony-v3a-g47-lr1e5ep1r64b32-W4A16 already exists in ChaiML
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Model already exists. Downloading to /tmp/model_output...
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Downloading snapshot of ChaiML/pony-v3a-g47-lr1e5ep1r64b32-W4A16...
2026-04-06T15:09:21.515044+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
2026-04-06T15:10:21.705541+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Downloaded in 69.499s
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Processed model ChaiML/pony-v3a-g47-lr1e5ep1r64b32 in 72.130s
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: creating bucket guanaco-vllm-models
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: uploading /tmp/model_output to s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/config.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/config.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/tokenizer_config.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/quantization_config.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model.safetensors.index.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/tokenizer.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/generation_config.json
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/chat_template.jinja
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/.gitattributes
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00038-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00038-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00037-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00037-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00036-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00036-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00022-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00022-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00007-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00007-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00023-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00023-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00002-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00002-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00013-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00013-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00001-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00001-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00006-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00006-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00016-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00016-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00010-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00010-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00011-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00011-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00019-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00019-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00003-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00003-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00027-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00027-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00035-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00035-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00030-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00030-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00015-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00015-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00009-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00009-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00034-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00034-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00031-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00031-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00021-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00021-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00012-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00012-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00014-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00014-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00005-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00005-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00028-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00028-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00024-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00024-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00029-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00029-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00004-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00004-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00008-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00008-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00017-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00017-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00033-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00033-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00026-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00026-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00025-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00025-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00032-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00032-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00018-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00018-of-00038.safetensors
chaiml-pony-v3a-g47-lr1-18022-v4-uploader: cp /tmp/model_output/model-00020-of-00038.safetensors s3://guanaco-vllm-models/chaiml-pony-v3a-g47-lr1-18022-v4/default/model-00020-of-00038.safetensors
Job chaiml-pony-v3a-g47-lr1-18022-v4-uploader completed after 176.25s with status: succeeded
Stopping job with name chaiml-pony-v3a-g47-lr1-18022-v4-uploader
Pipeline stage VLLMUploader completed in 176.84s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.12s
run pipeline stage %s
Running pipeline stage VLLMTemplater
2026-04-06T15:11:22.225245+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
Pipeline stage VLLMTemplater completed in 7.96s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-pony-v3a-g47-lr1-18022-v4
Waiting for inference service chaiml-pony-v3a-g47-lr1-18022-v4 to be ready
2026-04-06T15:12:22.413760+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
Retrying (%r) after connection broken by '%r': %s
2026-04-06T15:13:22.516232+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
Failed to get request counts for guanaco-submitter. Falling back to default
2026-04-06T15:14:22.618237+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
2026-04-06T15:15:22.716344+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
Inference service chaiml-pony-v3a-g47-lr1-18022-v4 ready after 250.92384910583496s
Pipeline stage VLLMDeployer completed in 251.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 8.960617303848267s
Received healthy response to inference request in 9.166636943817139s
Received healthy response to inference request in 2.77782940864563s
Received healthy response to inference request in 2.1267576217651367s
Received healthy response to inference request in 9.214423656463623s
Received healthy response to inference request in 1.9004793167114258s
2026-04-06T15:16:22.815914+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
Received healthy response to inference request in 9.484394073486328s
Received healthy response to inference request in 2.1826488971710205s
Received healthy response to inference request in 2.2948808670043945s
Received healthy response to inference request in 1.9689562320709229s
Received healthy response to inference request in 9.446610927581787s
Received healthy response to inference request in 2.109767436981201s
Received healthy response to inference request in 2.2142505645751953s
Received healthy response to inference request in 2.3679869174957275s
Received healthy response to inference request in 2.228644847869873s
Received healthy response to inference request in 2.0853917598724365s
Received healthy response to inference request in 2.1051793098449707s
Received healthy response to inference request in 2.1903557777404785s
Received healthy response to inference request in 2.2954530715942383s
Received healthy response to inference request in 2.2662014961242676s
Received healthy response to inference request in 2.239651918411255s
Received healthy response to inference request in 2.0592880249023438s
Received healthy response to inference request in 2.2612531185150146s
Received healthy response to inference request in 2.070038080215454s
Received healthy response to inference request in 2.138195753097534s
Received healthy response to inference request in 2.147789239883423s
Received healthy response to inference request in 2.1174793243408203s
Received healthy response to inference request in 2.306647300720215s
Received healthy response to inference request in 2.07674503326416s
Received healthy response to inference request in 2.6422970294952393s
30 requests
0 failed requests
5th percentile: 2.0096055388450624
10th percentile: 2.068963074684143
20th percentile: 2.101221799850464
30th percentile: 2.1239741325378416
2026-04-06T15:17:22.915628+00:00 monitor updated for chaiml-pony-v3a-g47-lr1_18022_v4
40th percentile: 2.1687050342559817
50th percentile: 2.221447706222534
60th percentile: 2.263232469558716
70th percentile: 2.298811340332031
80th percentile: 2.6694035053253176
90th percentile: 9.171415615081788
95th percentile: 9.342126655578612
99th percentile: 9.473436961174011
mean time: 3.3815617084503176
Pipeline stage StressChecker completed in 104.84s
Shutdown handler de-registered
chaiml-pony-v3a-g47-lr1_18022_v4 status is now deployed due to DeploymentManager action
chaiml-pony-v3a-g47-lr1_18022_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-pony-v3a-g47-lr1_18022_v4 status is now torndown due to DeploymentManager action