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-opusd-v4-q27b-lr1-4495-v2-uploader
Waiting for job on chaiml-opusd-v4-q27b-lr1-4495-v2-uploader to finish
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: Using quantization_mode: none
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: Downloading snapshot of ChaiML/opusd-v4-q27b-lr1e4ep2r64g4...
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: Downloaded in 35.517s
2026-03-22T03:52:05.064737+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: Processed model ChaiML/opusd-v4-q27b-lr1e4ep2r64g4 in 55.958s
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: creating bucket guanaco-vllm-models
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/.gitattributes
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/trainer_state.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/trainer_state.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/generation_config.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/chat_template.jinja
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/special_tokens_map.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/processor_config.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/processor_config.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/preprocessor_config.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/preprocessor_config.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/tokenizer_config.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/args.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/args.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/added_tokens.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/model.safetensors.index.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/training_args.bin s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/training_args.bin
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/config.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/README.md
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/merges.txt
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/vocab.json
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/tokenizer.json
2026-03-22T03:53:05.151505+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
chaiml-opusd-v4-q27b-lr1-4495-v2-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-opusd-v4-q27b-lr1-4495-v2/default/model-00001-of-00002.safetensors
Job chaiml-opusd-v4-q27b-lr1-4495-v2-uploader completed after 153.96s with status: succeeded
Stopping job with name chaiml-opusd-v4-q27b-lr1-4495-v2-uploader
Pipeline stage VLLMUploader completed in 154.44s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 3.01s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-opusd-v4-q27b-lr1-4495-v2
Waiting for inference service chaiml-opusd-v4-q27b-lr1-4495-v2 to be ready
2026-03-22T03:54:05.243616+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
2026-03-22T03:55:05.330347+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
2026-03-22T03:56:05.415662+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
Inference service chaiml-opusd-v4-q27b-lr1-4495-v2 ready after 170.27576208114624s
Pipeline stage VLLMDeployer completed in 170.74s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-22T03:57:05.510829+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 12.083722352981567s
2026-03-22T03:58:05.605699+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 4.840875148773193s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-22T03:59:05.947134+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 4.6244797706604s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.296903610229492s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.162761926651001s
Received healthy response to inference request in 2.241271495819092s
2026-03-22T04:00:06.041485+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
Received healthy response to inference request in 2.3257126808166504s
Received healthy response to inference request in 2.289166212081909s
Received healthy response to inference request in 2.337812900543213s
Received healthy response to inference request in 2.2633392810821533s
Received healthy response to inference request in 2.257826566696167s
Received healthy response to inference request in 4.617794752120972s
Received healthy response to inference request in 2.3093454837799072s
Received healthy response to inference request in 2.4110023975372314s
Received healthy response to inference request in 2.290092706680298s
Received healthy response to inference request in 2.31569766998291s
Received healthy response to inference request in 2.4632678031921387s
Received healthy response to inference request in 2.5036182403564453s
Received healthy response to inference request in 2.2340965270996094s
Received healthy response to inference request in 2.2437121868133545s
Received healthy response to inference request in 2.282247543334961s
30 requests
9 failed requests
5th percentile: 2.2373252630233766
10th percentile: 2.2434681177139284
20th percentile: 2.2784658908843993
30th percentile: 2.294860339164734
40th percentile: 2.321706676483154
50th percentile: 2.437135100364685
60th percentile: 4.6204687595367435
70th percentile: 14.493774986267066
80th percentile: 20.13264718055725
90th percentile: 20.15913815498352
95th percentile: 20.190605878829956
99th percentile: 20.37599911928177
mean time: 8.234255639712016
%s, retrying in %s seconds...
Received healthy response to inference request in 2.067129135131836s
Received healthy response to inference request in 2.0657029151916504s
Received healthy response to inference request in 2.178936719894409s
Received healthy response to inference request in 2.1562740802764893s
Received healthy response to inference request in 2.108513832092285s
Received healthy response to inference request in 2.1962411403656006s
Received healthy response to inference request in 2.5933432579040527s
Received healthy response to inference request in 2.3718912601470947s
Received healthy response to inference request in 2.2884535789489746s
Received healthy response to inference request in 2.2862343788146973s
2026-03-22T04:01:06.140538+00:00 monitor updated for chaiml-opusd-v4-q27b-lr1_4495_v2
Received healthy response to inference request in 2.139958143234253s
Received healthy response to inference request in 2.2309446334838867s
Received healthy response to inference request in 2.2570271492004395s
Received healthy response to inference request in 2.2545313835144043s
Received healthy response to inference request in 2.2476108074188232s
Received healthy response to inference request in 2.305372476577759s
Received healthy response to inference request in 2.172189474105835s
Received healthy response to inference request in 2.286817789077759s
Received healthy response to inference request in 2.183609962463379s
Received healthy response to inference request in 2.308126211166382s
Received healthy response to inference request in 2.45975923538208s
Received healthy response to inference request in 2.416731119155884s
Received healthy response to inference request in 2.1529417037963867s
Received healthy response to inference request in 2.230451822280884s
Received healthy response to inference request in 2.125581979751587s
Received healthy response to inference request in 2.3009390830993652s
Received healthy response to inference request in 2.3183350563049316s
Received healthy response to inference request in 2.125236749649048s
Received healthy response to inference request in 2.481283187866211s
Received healthy response to inference request in 2.2600183486938477s
30 requests
0 failed requests
5th percentile: 2.085752248764038
10th percentile: 2.1235644578933717
20th percentile: 2.15034499168396
30th percentile: 2.176912546157837
40th percentile: 2.2167675495147705
50th percentile: 2.2510710954666138
60th percentile: 2.2705047607421873
70th percentile: 2.292199230194092
80th percentile: 2.310167980194092
90th percentile: 2.4210339307785036
95th percentile: 2.471597409248352
99th percentile: 2.560845837593079
mean time: 2.252339553833008
Pipeline stage StressChecker completed in 320.28s
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 1.46s
Shutdown handler de-registered
chaiml-opusd-v4-q27b-lr1_4495_v2 status is now deployed due to DeploymentManager action
chaiml-opusd-v4-q27b-lr1_4495_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-opusd-v4-q27b-lr1_4495_v2 status is now torndown due to DeploymentManager action