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-d-39140-v7-uploader
Waiting for job on chaiml-merged-qwen-35-d-39140-v7-uploader to finish
chaiml-merged-qwen-35-d-39140-v7-uploader: Using quantization_mode: none
chaiml-merged-qwen-35-d-39140-v7-uploader: Downloading snapshot of ChaiML/merged_qwen_35_dpo_lower_lr_v...
chaiml-merged-qwen-35-d-39140-v7-uploader: Downloaded in 31.447s
2026-03-27T15:50:10.774982+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
chaiml-merged-qwen-35-d-39140-v7-uploader: Processed model ChaiML/merged_qwen_35_dpo_lower_lr_v in 51.910s
chaiml-merged-qwen-35-d-39140-v7-uploader: creating bucket guanaco-vllm-models
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-d-39140-v7-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-merged-qwen-35-d-39140-v7-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-d-39140-v7-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-d-39140-v7-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-d-39140-v7-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-d-39140-v7-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-merged-qwen-35-d-39140-v7-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-merged-qwen-35-d-39140-v7-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-merged-qwen-35-d-39140-v7-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-merged-qwen-35-d-39140-v7-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-merged-qwen-35-d-39140-v7-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/README.md
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/config.json
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/generation_config.json
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/model.safetensors.index.json
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/tokenizer_config.json
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/.gitattributes
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/tokenizer.json
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/model-00002-of-00002.safetensors
2026-03-27T15:51:10.871479+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
chaiml-merged-qwen-35-d-39140-v7-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-d-39140-v7/default/model-00001-of-00002.safetensors
Job chaiml-merged-qwen-35-d-39140-v7-uploader completed after 143.03s with status: succeeded
Stopping job with name chaiml-merged-qwen-35-d-39140-v7-uploader
Pipeline stage VLLMUploader completed in 143.54s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 3.16s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-merged-qwen-35-d-39140-v7
Waiting for inference service chaiml-merged-qwen-35-d-39140-v7 to be ready
2026-03-27T15:52:10.961021+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
2026-03-27T15:53:11.057299+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
2026-03-27T15:54:11.166701+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
Inference service chaiml-merged-qwen-35-d-39140-v7 ready after 180.6197910308838s
Pipeline stage VLLMDeployer completed in 181.25s
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!
2026-03-27T15:55:11.262687+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
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!
2026-03-27T15:56:11.365395+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
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 9.405150651931763s
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!
2026-03-27T15:57:11.465431+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
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 2.625983476638794s
Received healthy response to inference request in 2.5200634002685547s
Received healthy response to inference request in 2.552771806716919s
Received healthy response to inference request in 9.295014381408691s
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 2.7796096801757812s
Received healthy response to inference request in 9.561945915222168s
2026-03-27T15:58:11.565537+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
Received healthy response to inference request in 2.984544277191162s
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 2.6107752323150635s
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!
Retrying (%r) after connection broken by '%r': %s
2026-03-27T15:59:11.688249+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
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 2.946319818496704s
Received healthy response to inference request in 2.461077928543091s
Received healthy response to inference request in 2.7078282833099365s
Received healthy response to inference request in 2.973928689956665s
Received healthy response to inference request in 2.7472522258758545s
Received healthy response to inference request in 2.6957767009735107s
Received healthy response to inference request in 2.5774192810058594s
Received healthy response to inference request in 9.649831533432007s
Received healthy response to inference request in 2.628214120864868s
Received healthy response to inference request in 2.6222054958343506s
30 requests
11 failed requests
5th percentile: 2.534782183170319
10th percentile: 2.5749545335769652
20th percentile: 2.6252278804779055
30th percentile: 2.7042128086090087
40th percentile: 2.879635763168335
50th percentile: 6.139779329299927
60th percentile: 9.597100162506104
70th percentile: 20.119126868247985
80th percentile: 20.122632455825805
90th percentile: 20.135590529441835
95th percentile: 20.15067368745804
99th percentile: 27.701997382640847
mean time: 10.3470667997996
%s, retrying in %s seconds...
Received healthy response to inference request in 2.535762310028076s
Received healthy response to inference request in 2.5320913791656494s
Received healthy response to inference request in 2.450808048248291s
Received healthy response to inference request in 2.558734655380249s
Received healthy response to inference request in 2.540923833847046s
Received healthy response to inference request in 2.7744758129119873s
Received healthy response to inference request in 2.4305689334869385s
2026-03-27T16:00:11.796618+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
Received healthy response to inference request in 2.5435962677001953s
Received healthy response to inference request in 2.524186611175537s
Received healthy response to inference request in 2.5636744499206543s
Received healthy response to inference request in 2.4864752292633057s
Received healthy response to inference request in 2.729173421859741s
Received healthy response to inference request in 2.5911357402801514s
Received healthy response to inference request in 2.799483299255371s
Received healthy response to inference request in 2.5435640811920166s
Received healthy response to inference request in 2.6116230487823486s
Received healthy response to inference request in 2.4829561710357666s
Received healthy response to inference request in 2.9682278633117676s
Received healthy response to inference request in 2.571465253829956s
Received healthy response to inference request in 2.6885838508605957s
Received healthy response to inference request in 2.743835210800171s
Received healthy response to inference request in 2.4975099563598633s
Received healthy response to inference request in 2.5949692726135254s
Received healthy response to inference request in 2.6027703285217285s
Received healthy response to inference request in 2.6013343334198s
Received healthy response to inference request in 2.7824206352233887s
2026-03-27T16:01:11.917389+00:00 monitor updated for chaiml-merged-qwen-35-d_39140_v7
Received healthy response to inference request in 2.6466712951660156s
Received healthy response to inference request in 2.637660264968872s
Received healthy response to inference request in 2.8238604068756104s
Received healthy response to inference request in 2.7685954570770264s
30 requests
0 failed requests
5th percentile: 2.465274703502655
10th percentile: 2.4861233234405518
20th percentile: 2.530510425567627
30th percentile: 2.5427720069885256
40th percentile: 2.5616985321044923
50th percentile: 2.5930525064468384
60th percentile: 2.6063114166259767
70th percentile: 2.6592450618743895
80th percentile: 2.748787260055542
90th percentile: 2.784126901626587
95th percentile: 2.8128907084465027
99th percentile: 2.926361300945282
mean time: 2.620904580752055
Pipeline stage StressChecker completed in 404.60s
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 0.74s
Shutdown handler de-registered
chaiml-merged-qwen-35-d_39140_v7 status is now deployed due to DeploymentManager action
chaiml-merged-qwen-35-d_39140_v7 status is now inactive due to auto deactivation removed underperforming models