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-live-rm-qwen-235-26530-v2-uploader
Waiting for job on chaiml-live-rm-qwen-235-26530-v2-uploader to finish
chaiml-live-rm-qwen-235-26530-v2-uploader: Using quantization_mode: none
chaiml-live-rm-qwen-235-26530-v2-uploader: Downloading snapshot of ChaiML/live_rm_qwen_235b_1024_cp350_lr2...
chaiml-live-rm-qwen-235-26530-v2-uploader: Downloaded in 10.659s
chaiml-live-rm-qwen-235-26530-v2-uploader: Processed model ChaiML/live_rm_qwen_235b_1024_cp350_lr2 in 16.631s
chaiml-live-rm-qwen-235-26530-v2-uploader: creating bucket guanaco-vllm-models
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-live-rm-qwen-235-26530-v2-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-live-rm-qwen-235-26530-v2-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-live-rm-qwen-235-26530-v2-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-live-rm-qwen-235-26530-v2-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-live-rm-qwen-235-26530-v2-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-live-rm-qwen-235-26530-v2-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-live-rm-qwen-235-26530-v2-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-live-rm-qwen-235-26530-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-live-rm-qwen-235-26530-v2-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-live-rm-qwen-235-26530-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-live-rm-qwen-235-26530-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/README.md
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/tokenizer_config.json
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/special_tokens_map.json
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/.gitattributes
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/model.safetensors.index.json
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/config.json
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/tokenizer.json
chaiml-live-rm-qwen-235-26530-v2-uploader: cp /dev/shm/model_output/model-00004-of-00004.safetensors s3://guanaco-vllm-models/chaiml-live-rm-qwen-235-26530-v2/default/model-00004-of-00004.safetensors
Job chaiml-live-rm-qwen-235-26530-v2-uploader completed after 42.97s with status: succeeded
Stopping job with name chaiml-live-rm-qwen-235-26530-v2-uploader
Pipeline stage VLLMUploader completed in 47.17s
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-live-rm-qwen-235-26530-v2
Waiting for inference service chaiml-live-rm-qwen-235-26530-v2 to be ready
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-live-rm-qwen-235-26530-v2 ready after 171.3765366077423s
Pipeline stage VLLMDeployer completed in 171.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.78676438331604s
Received healthy response to inference request in 4.0107262134552s
Received healthy response to inference request in 5.126958608627319s
Received healthy response to inference request in 3.0279600620269775s
Received healthy response to inference request in 4.223777770996094s
5 requests
0 failed requests
5th percentile: 3.224513292312622
10th percentile: 3.4210665225982666
20th percentile: 3.8141729831695557
30th percentile: 4.053336524963379
40th percentile: 4.1385571479797365
50th percentile: 4.223777770996094
60th percentile: 4.448972415924072
70th percentile: 4.67416706085205
80th percentile: 4.854803228378296
90th percentile: 4.990880918502808
95th percentile: 5.058919763565063
99th percentile: 5.113350839614868
mean time: 4.235237407684326
Pipeline stage StressChecker completed in 22.53s
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 0.60s
Shutdown handler de-registered
chaiml-live-rm-qwen-235_26530_v2 status is now deployed due to DeploymentManager action
chaiml-live-rm-qwen-235_26530_v2 status is now inactive due to auto deactivation removed underperforming models