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-dpo-v-v1-uploader
Waiting for job on chaiml-merged-qwen-35-dpo-v-v1-uploader to finish
chaiml-merged-qwen-35-dpo-v-v1-uploader: Using quantization_mode: none
chaiml-merged-qwen-35-dpo-v-v1-uploader: Downloading snapshot of ChaiML/merged_qwen_35_dpo_v...
chaiml-merged-qwen-35-dpo-v-v1-uploader: Downloaded in 30.809s
chaiml-merged-qwen-35-dpo-v-v1-uploader: Processed model ChaiML/merged_qwen_35_dpo_v in 50.880s
2026-03-24T06:25:23.849819+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
chaiml-merged-qwen-35-dpo-v-v1-uploader: cp /dev/shm/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-dpo-v-v1/default/model-00002-of-00002.safetensors
2026-03-24T06:26:29.332136+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
chaiml-merged-qwen-35-dpo-v-v1-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-dpo-v-v1/default/model-00001-of-00002.safetensors
Job chaiml-merged-qwen-35-dpo-v-v1-uploader completed after 145.23s with status: succeeded
Stopping job with name chaiml-merged-qwen-35-dpo-v-v1-uploader
Pipeline stage VLLMUploader completed in 145.73s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.63s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-merged-qwen-35-dpo-v-v1
Waiting for inference service chaiml-merged-qwen-35-dpo-v-v1 to be ready
2026-03-24T06:27:29.443748+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
2026-03-24T06:28:29.537216+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
2026-03-24T06:29:29.632621+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
Inference service chaiml-merged-qwen-35-dpo-v-v1 ready after 180.5015320777893s
Pipeline stage VLLMDeployer completed in 181.11s
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!
2026-03-24T06:30:29.727973+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
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!
2026-03-24T06:31:29.821138+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
Received healthy response to inference request in 17.644537210464478s
Received healthy response to inference request in 9.649049043655396s
Received healthy response to inference request in 2.675889492034912s
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!
2026-03-24T06:32:29.913597+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
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 18.177841663360596s
Received healthy response to inference request in 9.62040114402771s
Received healthy response to inference request in 2.660914421081543s
Received healthy response to inference request in 2.700436592102051s
Received healthy response to inference request in 10.53664255142212s
2026-03-24T06:33:30.006024+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
Received healthy response to inference request in 2.961672306060791s
Received healthy response to inference request in 2.602883815765381s
Received healthy response to inference request in 2.839069366455078s
Received healthy response to inference request in 2.689483880996704s
Received healthy response to inference request in 2.5812478065490723s
Received healthy response to inference request in 2.9068472385406494s
Received healthy response to inference request in 2.6587376594543457s
Received healthy response to inference request in 2.6254231929779053s
Received healthy response to inference request in 2.639472723007202s
Received healthy response to inference request in 2.6897189617156982s
Received healthy response to inference request in 2.718933582305908s
Received healthy response to inference request in 2.7326254844665527s
Received healthy response to inference request in 2.7510857582092285s
Received healthy response to inference request in 2.7218196392059326s
Received healthy response to inference request in 2.660168409347534s
30 requests
7 failed requests
5th percentile: 2.613026535511017
10th percentile: 2.6380677700042723
20th percentile: 2.660765218734741
30th percentile: 2.6896484375
40th percentile: 2.720665216445923
50th percentile: 2.7950775623321533
60th percentile: 5.625163841247549
70th percentile: 12.669010949134806
80th percentile: 20.119562005996706
90th percentile: 20.12514181137085
95th percentile: 20.133101439476015
99th percentile: 20.144143965244293
mean time: 8.511460328102112
%s, retrying in %s seconds...
Received healthy response to inference request in 2.6989846229553223s
Received healthy response to inference request in 2.4855408668518066s
Received healthy response to inference request in 2.623076915740967s
Received healthy response to inference request in 2.542548418045044s
Received healthy response to inference request in 2.605842351913452s
Received healthy response to inference request in 2.5190012454986572s
Received healthy response to inference request in 2.660583019256592s
2026-03-24T06:34:30.104537+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
Received healthy response to inference request in 2.600407838821411s
Received healthy response to inference request in 2.7188282012939453s
Received healthy response to inference request in 2.643348455429077s
Received healthy response to inference request in 2.681239604949951s
Received healthy response to inference request in 2.580570936203003s
Received healthy response to inference request in 2.6556050777435303s
Received healthy response to inference request in 2.6105170249938965s
Received healthy response to inference request in 2.65716290473938s
Received healthy response to inference request in 2.4834418296813965s
Received healthy response to inference request in 2.6415884494781494s
Received healthy response to inference request in 2.7841391563415527s
Received healthy response to inference request in 3.0091042518615723s
Received healthy response to inference request in 2.8421452045440674s
Received healthy response to inference request in 2.6351096630096436s
Received healthy response to inference request in 2.8458752632141113s
Received healthy response to inference request in 2.7108049392700195s
Received healthy response to inference request in 2.545682430267334s
Received healthy response to inference request in 2.719727039337158s
Received healthy response to inference request in 2.7670819759368896s
Received healthy response to inference request in 2.6490068435668945s
Received healthy response to inference request in 2.8613228797912598s
2026-03-24T06:35:30.278093+00:00 monitor updated for chaiml-merged-qwen-35-dpo-v_v1
Received healthy response to inference request in 2.724112033843994s
Received healthy response to inference request in 2.8342461585998535s
30 requests
0 failed requests
5th percentile: 2.5005980372428893
10th percentile: 2.540193700790405
20th percentile: 2.5964404582977294
30th percentile: 2.6193089485168457
40th percentile: 2.642644453048706
50th percentile: 2.656383991241455
60th percentile: 2.6883376121520994
70th percentile: 2.719097852706909
80th percentile: 2.770493412017822
90th percentile: 2.8425182104110718
95th percentile: 2.854371452331543
99th percentile: 2.9662476539611817
mean time: 2.6778881867726643
Pipeline stage StressChecker completed in 341.76s
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 1.53s
Shutdown handler de-registered
chaiml-merged-qwen-35-dpo-v_v1 status is now deployed due to DeploymentManager action
chaiml-merged-qwen-35-dpo-v_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-merged-qwen-35-dpo-v_v1 status is now torndown due to DeploymentManager action