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-7b07-69d4-linear-27339-v7-uploader
Waiting for job on chaiml-7b07-69d4-linear-27339-v7-uploader to finish
Retrying (%r) after connection broken by '%r': %s
Retrying (%r) after connection broken by '%r': %s
chaiml-7b07-69d4-linear-27339-v7-uploader: Using quantization_mode: fp8
chaiml-7b07-69d4-linear-27339-v7-uploader: Repo ChaiML/7b07-69d4-linear-w01-FP8 already ends in FP8. Skipping...
chaiml-7b07-69d4-linear-27339-v7-uploader: Checking if ChaiML/7b07-69d4-linear-w01-FP8 already exists in ChaiML
chaiml-7b07-69d4-linear-27339-v7-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-7b07-69d4-linear-27339-v7-uploader: Downloading snapshot of ChaiML/7b07-69d4-linear-w01-FP8...
chaiml-7b07-69d4-linear-27339-v7-uploader: Downloaded in 13.103s
chaiml-7b07-69d4-linear-27339-v7-uploader: Processed model ChaiML/7b07-69d4-linear-w01-FP8 in 16.678s
chaiml-7b07-69d4-linear-27339-v7-uploader: creating bucket guanaco-vllm-models
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-7b07-69d4-linear-27339-v7-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-7b07-69d4-linear-27339-v7-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-7b07-69d4-linear-27339-v7-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-7b07-69d4-linear-27339-v7-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-7b07-69d4-linear-27339-v7-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-7b07-69d4-linear-27339-v7-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-7b07-69d4-linear-27339-v7-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-7b07-69d4-linear-27339-v7-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-7b07-69d4-linear-27339-v7-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/tokenizer.json
HTTP Request: %s %s "%s %d %s"
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00006-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00006-of-00006.safetensors
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00005-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00005-of-00006.safetensors
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00002-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00002-of-00006.safetensors
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00004-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00004-of-00006.safetensors
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00003-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00003-of-00006.safetensors
chaiml-7b07-69d4-linear-27339-v7-uploader: cp /dev/shm/model_output/model-00001-of-00006.safetensors s3://guanaco-vllm-models/chaiml-7b07-69d4-linear-27339-v7/default/model-00001-of-00006.safetensors
Job chaiml-7b07-69d4-linear-27339-v7-uploader completed after 134.15s with status: succeeded
Stopping job with name chaiml-7b07-69d4-linear-27339-v7-uploader
Pipeline stage VLLMUploader completed in 134.69s
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-7b07-69d4-linear-27339-v7
Waiting for inference service chaiml-7b07-69d4-linear-27339-v7 to be ready
Inference service chaiml-7b07-69d4-linear-27339-v7 ready after 140.67902326583862s
Pipeline stage VLLMDeployer completed in 141.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.781008243560791s
Received healthy response to inference request in 2.7225048542022705s
Received healthy response to inference request in 2.5746610164642334s
Received healthy response to inference request in 2.6803061962127686s
Received healthy response to inference request in 2.7019574642181396s
Received healthy response to inference request in 2.5222420692443848s
Received healthy response to inference request in 2.976940155029297s
Received healthy response to inference request in 2.902132272720337s
Received healthy response to inference request in 2.8155455589294434s
Received healthy response to inference request in 2.7053678035736084s
Received healthy response to inference request in 3.050710916519165s
Received healthy response to inference request in 2.5404183864593506s
Received healthy response to inference request in 2.976900100708008s
Received healthy response to inference request in 2.6679494380950928s
Received healthy response to inference request in 2.581803321838379s
Received healthy response to inference request in 2.9408771991729736s
Received healthy response to inference request in 2.9648666381835938s
Received healthy response to inference request in 2.8748838901519775s
Received healthy response to inference request in 2.6084558963775635s
Received healthy response to inference request in 2.7096152305603027s
Received healthy response to inference request in 2.545161724090576s
Received healthy response to inference request in 2.679412841796875s
Received healthy response to inference request in 2.5242815017700195s
Received healthy response to inference request in 2.632523775100708s
Received healthy response to inference request in 2.7015647888183594s
Received healthy response to inference request in 2.5160679817199707s
Received healthy response to inference request in 3.07487416267395s
Received healthy response to inference request in 2.711399793624878s
Received healthy response to inference request in 2.721970796585083s
Received healthy response to inference request in 2.7229814529418945s
30 requests
0 failed requests
5th percentile: 2.5231598138809206
10th percentile: 2.5388046979904173
20th percentile: 2.5803748607635497
30th percentile: 2.657321739196777
40th percentile: 2.693061351776123
50th percentile: 2.7074915170669556
60th percentile: 2.722184419631958
70th percentile: 2.7913694381713867
80th percentile: 2.909881258010864
90th percentile: 2.976904106140137
95th percentile: 3.0175140738487243
99th percentile: 3.0678668212890625
mean time: 2.7376461823781333
Pipeline stage StressChecker completed in 85.09s
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 0.63s
Shutdown handler de-registered
chaiml-7b07-69d4-linear_27339_v7 status is now deployed due to DeploymentManager action
chaiml-7b07-69d4-linear_27339_v7 status is now inactive due to system request