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-prm-kimi-v1-300k-92220-v8-uploader
Waiting for job on chaiml-prm-kimi-v1-300k-92220-v8-uploader to finish
chaiml-prm-kimi-v1-300k-92220-v8-uploader: Using quantization_mode: none
chaiml-prm-kimi-v1-300k-92220-v8-uploader: Downloading snapshot of ChaiML/prm_kimi_v1_300k_default8b-cosine-lr1e6g32...
chaiml-prm-kimi-v1-300k-92220-v8-uploader: Downloaded in 6.977s
chaiml-prm-kimi-v1-300k-92220-v8-uploader: Processed model ChaiML/prm_kimi_v1_300k_default8b-cosine-lr1e6g32 in 12.524s
chaiml-prm-kimi-v1-300k-92220-v8-uploader: creating bucket guanaco-vllm-models
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-prm-kimi-v1-300k-92220-v8-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-prm-kimi-v1-300k-92220-v8-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-prm-kimi-v1-300k-92220-v8-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-prm-kimi-v1-300k-92220-v8-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/.gitattributes
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/special_tokens_map.json
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/README.md
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/model.safetensors.index.json
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/tokenizer_config.json
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/config.json
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/tokenizer.json
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/model-00003-of-00004.safetensors s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/model-00003-of-00004.safetensors
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/model-00001-of-00004.safetensors s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/model-00001-of-00004.safetensors
chaiml-prm-kimi-v1-300k-92220-v8-uploader: cp /dev/shm/model_output/model-00002-of-00004.safetensors s3://guanaco-vllm-models/chaiml-prm-kimi-v1-300k-92220-v8/default/model-00002-of-00004.safetensors
Job chaiml-prm-kimi-v1-300k-92220-v8-uploader completed after 34.92s with status: succeeded
Stopping job with name chaiml-prm-kimi-v1-300k-92220-v8-uploader
Pipeline stage VLLMUploader completed in 36.18s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-prm-kimi-v1-300k-92220-v8
Waiting for inference service chaiml-prm-kimi-v1-300k-92220-v8 to be ready
Inference service chaiml-prm-kimi-v1-300k-92220-v8 ready after 160.62286901474s
Pipeline stage VLLMDeployer completed in 162.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.16472315788269s
Received healthy response to inference request in 2.946784734725952s
Received healthy response to inference request in 4.662168264389038s
Received healthy response to inference request in 4.507981061935425s
Received healthy response to inference request in 4.05816650390625s
5 requests
0 failed requests
5th percentile: 3.1690610885620116
10th percentile: 3.391337442398071
20th percentile: 3.8358901500701905
30th percentile: 4.079477834701538
40th percentile: 4.122100496292115
50th percentile: 4.16472315788269
60th percentile: 4.302026319503784
70th percentile: 4.439329481124878
80th percentile: 4.538818502426148
90th percentile: 4.600493383407593
95th percentile: 4.631330823898315
99th percentile: 4.6560007762908935
mean time: 4.067964744567871
Pipeline stage StressChecker completed in 21.48s
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 0.86s
Shutdown handler de-registered
chaiml-prm-kimi-v1-300k_92220_v8 status is now deployed due to DeploymentManager action
chaiml-prm-kimi-v1-300k_92220_v8 status is now inactive due to auto deactivation removed underperforming models
chaiml-prm-kimi-v1-300k_92220_v8 status is now torndown due to DeploymentManager action