Shutdown handler not registered because Python interpreter is not running in the main thread
Retrying (%r) after connection broken by '%r': %s
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Retrying (%r) after connection broken by '%r': %s
Starting job with name chaiml-llama31-mer-v2-44570-v88-uploader
Waiting for job on chaiml-llama31-mer-v2-44570-v88-uploader to finish
chaiml-llama31-mer-v2-44570-v88-uploader: Using quantization_mode: none
chaiml-llama31-mer-v2-44570-v88-uploader: Downloading snapshot of ChaiML/llama31-mer-v2-try1-new8m-filterv3-full-512seq-bestep-572...
Failed to get response for submission chaiml-grpo-q235b-kimid_37540_v1: HTTPConnectionPool(host='chaiml-grpo-q235b-kimid-37540-v1-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-llama31-mer-v2-44570-v88-uploader: Downloaded in 7.828s
chaiml-llama31-mer-v2-44570-v88-uploader: creating bucket guanaco-vllm-models
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-llama31-mer-v2-44570-v88-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-llama31-mer-v2-44570-v88-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-llama31-mer-v2-44570-v88-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-llama31-mer-v2-44570-v88-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-llama31-mer-v2-44570-v88-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-llama31-mer-v2-44570-v88-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-llama31-mer-v2-44570-v88-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-llama31-mer-v2-44570-v88-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-llama31-mer-v2-44570-v88-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-llama31-mer-v2-44570-v88-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-llama31-mer-v2-44570-v88-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/README.md
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/model.safetensors.index.json
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/.gitattributes
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/special_tokens_map.json
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/tokenizer_config.json
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/config.json
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/tokenizer.json
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/model-00004-of-00004.safetensors s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/model-00004-of-00004.safetensors
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/model-00001-of-00004.safetensors s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/model-00001-of-00004.safetensors
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/model-00003-of-00004.safetensors s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/model-00003-of-00004.safetensors
chaiml-llama31-mer-v2-44570-v88-uploader: cp /dev/shm/model_output/model-00002-of-00004.safetensors s3://guanaco-vllm-models/chaiml-llama31-mer-v2-44570-v88/default/model-00002-of-00004.safetensors
Job chaiml-llama31-mer-v2-44570-v88-uploader completed after 45.6s with status: succeeded
Stopping job with name chaiml-llama31-mer-v2-44570-v88-uploader
Pipeline stage VLLMUploader completed in 46.32s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.34s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-llama31-mer-v2-44570-v88
Waiting for inference service chaiml-llama31-mer-v2-44570-v88 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-llama31-mer-v2-44570-v88 ready after 151.05100917816162s
Pipeline stage VLLMDeployer completed in 151.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6914734840393066s
Received healthy response to inference request in 3.564053535461426s
Received healthy response to inference request in 2.0903806686401367s
Received healthy response to inference request in 4.334611892700195s
Received healthy response to inference request in 2.282485008239746s
5 requests
0 failed requests
5th percentile: 2.1288015365600588
10th percentile: 2.1672224044799804
20th percentile: 2.244064140319824
30th percentile: 2.538798713684082
40th percentile: 3.051426124572754
50th percentile: 3.564053535461426
60th percentile: 3.615021514892578
70th percentile: 3.6659894943237306
80th percentile: 3.8201011657714843
90th percentile: 4.07735652923584
95th percentile: 4.205984210968017
99th percentile: 4.30888635635376
mean time: 3.1926009178161623
Pipeline stage StressChecker completed in 17.13s
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-llama31-mer-v2-_44570_v88 status is now deployed due to DeploymentManager action
chaiml-llama31-mer-v2-_44570_v88 status is now inactive due to auto deactivation removed underperforming models