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-merged-qwen-35-39140-v20-uploader
Waiting for job on chaiml-merged-qwen-35-39140-v20-uploader to finish
chaiml-merged-qwen-35-39140-v20-uploader: Using quantization_mode: none
chaiml-merged-qwen-35-39140-v20-uploader: Downloading snapshot of ChaiML/merged_qwen_35_dpo_lower_lr_v...
chaiml-merged-qwen-35-39140-v20-uploader: Downloaded in 31.553s
2026-03-28T17:22:53.580173+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
chaiml-merged-qwen-35-39140-v20-uploader: Processed model ChaiML/merged_qwen_35_dpo_lower_lr_v in 51.805s
chaiml-merged-qwen-35-39140-v20-uploader: creating bucket guanaco-vllm-models
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v20-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-merged-qwen-35-39140-v20-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v20-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v20-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v20-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v20-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-merged-qwen-35-39140-v20-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-merged-qwen-35-39140-v20-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-merged-qwen-35-39140-v20-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-merged-qwen-35-39140-v20-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-merged-qwen-35-39140-v20-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/.gitattributes
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/model.safetensors.index.json
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/config.json
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/generation_config.json
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/README.md
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/tokenizer_config.json
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/tokenizer.json
2026-03-28T17:23:53.667528+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
chaiml-merged-qwen-35-39140-v20-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v20/default/model-00001-of-00002.safetensors
Job chaiml-merged-qwen-35-39140-v20-uploader completed after 162.76s with status: succeeded
Stopping job with name chaiml-merged-qwen-35-39140-v20-uploader
Pipeline stage VLLMUploader completed in 163.46s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.96s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-merged-qwen-35-39140-v20
Waiting for inference service chaiml-merged-qwen-35-39140-v20 to be ready
2026-03-28T17:24:53.764533+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
2026-03-28T17:25:53.864362+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
2026-03-28T17:26:53.961902+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
Inference service chaiml-merged-qwen-35-39140-v20 ready after 170.39931893348694s
Pipeline stage VLLMDeployer completed in 170.92s
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!
2026-03-28T17:27:54.062987+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
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!
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!
2026-03-28T17:28:54.156666+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
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!
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!
2026-03-28T17:29:54.260765+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
Received healthy response to inference request in 9.662280321121216s
Received healthy response to inference request in 9.888566493988037s
Received healthy response to inference request in 2.6827521324157715s
Received healthy response to inference request in 9.190216064453125s
Received healthy response to inference request in 9.501448392868042s
Received healthy response to inference request in 2.5303432941436768s
Received healthy response to inference request in 9.625718832015991s
Received healthy response to inference request in 2.582096815109253s
Received healthy response to inference request in 2.8964786529541016s
Received healthy response to inference request in 2.4583258628845215s
2026-03-28T17:30:54.358092+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
Received healthy response to inference request in 2.7008771896362305s
Received healthy response to inference request in 2.6737468242645264s
Received healthy response to inference request in 2.592609167098999s
Received healthy response to inference request in 2.9007604122161865s
Received healthy response to inference request in 2.5784642696380615s
Received healthy response to inference request in 2.645901679992676s
Received healthy response to inference request in 2.6897897720336914s
Received healthy response to inference request in 2.603696346282959s
Received healthy response to inference request in 2.7003185749053955s
Received healthy response to inference request in 2.738034963607788s
Received healthy response to inference request in 2.644490957260132s
Received healthy response to inference request in 2.6142947673797607s
Received healthy response to inference request in 2.6418159008026123s
30 requests
7 failed requests
5th percentile: 2.55199773311615
10th percentile: 2.581733560562134
20th percentile: 2.6121750831604005
30th percentile: 2.6454784631729127
40th percentile: 2.6869747161865236
50th percentile: 2.7194560766220093
60th percentile: 5.416542673110953
70th percentile: 9.636687278747559
80th percentile: 20.114170837402344
90th percentile: 20.12873592376709
95th percentile: 20.13247526884079
99th percentile: 20.135166037082673
mean time: 7.887294944127401
%s, retrying in %s seconds...
Received healthy response to inference request in 2.494743824005127s
Received healthy response to inference request in 2.5169899463653564s
Received healthy response to inference request in 2.5061826705932617s
Received healthy response to inference request in 2.612715005874634s
Received healthy response to inference request in 2.386615037918091s
Received healthy response to inference request in 2.56180477142334s
Received healthy response to inference request in 2.4333183765411377s
Received healthy response to inference request in 2.48976731300354s
Received healthy response to inference request in 2.543008804321289s
2026-03-28T17:31:54.451759+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v20
Received healthy response to inference request in 2.3916611671447754s
Received healthy response to inference request in 2.5360052585601807s
Received healthy response to inference request in 2.916118860244751s
Received healthy response to inference request in 2.6891465187072754s
Received healthy response to inference request in 2.607628107070923s
Received healthy response to inference request in 2.6993680000305176s
Received healthy response to inference request in 2.5682053565979004s
Received healthy response to inference request in 2.501540184020996s
Received healthy response to inference request in 2.5324816703796387s
Received healthy response to inference request in 2.710649013519287s
Received healthy response to inference request in 2.5694375038146973s
Received healthy response to inference request in 2.614349365234375s
Received healthy response to inference request in 2.8956055641174316s
Received healthy response to inference request in 2.6117351055145264s
Received healthy response to inference request in 2.6299917697906494s
Received healthy response to inference request in 2.7380740642547607s
Received healthy response to inference request in 2.628082513809204s
Received healthy response to inference request in 2.5716841220855713s
Received healthy response to inference request in 2.583284854888916s
Received healthy response to inference request in 2.791897773742676s
Received healthy response to inference request in 2.6285603046417236s
30 requests
0 failed requests
5th percentile: 2.4104069113731383
10th percentile: 2.4841224193572997
20th percentile: 2.5052541732788085
30th percentile: 2.5349481821060182
40th percentile: 2.565645122528076
50th percentile: 2.5774844884872437
60th percentile: 2.6121270656585693
70th percentile: 2.62822585105896
80th percentile: 2.691190814971924
90th percentile: 2.7434564352035524
95th percentile: 2.8489370584487914
99th percentile: 2.9101700043678282
mean time: 2.5986884276072186
Pipeline stage StressChecker completed in 319.33s
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 0.67s
Shutdown handler de-registered
chaiml-merged-qwen-35-_39140_v20 status is now deployed due to DeploymentManager action
chaiml-merged-qwen-35-_39140_v20 status is now inactive due to admin request