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 evelyn777-chai-sft-3b-v5-v1-uploader
Waiting for job on evelyn777-chai-sft-3b-v5-v1-uploader to finish
evelyn777-chai-sft-3b-v5-v1-uploader: Using quantization_mode: none
evelyn777-chai-sft-3b-v5-v1-uploader: Downloading snapshot of evelyn777/chai-sft-3b-v5...
evelyn777-chai-sft-3b-v5-v1-uploader: 
Fetching 13 files:   0%|          | 0/13 [00:00<?, ?it/s]
Fetching 13 files:   8%|▊         | 1/13 [00:00<00:03,  3.57it/s]
Fetching 13 files:  46%|████▌     | 6/13 [00:00<00:00, 17.13it/s]
Fetching 13 files:  69%|██████▉   | 9/13 [00:04<00:02,  1.73it/s]
Fetching 13 files: 100%|██████████| 13/13 [00:04<00:00,  3.08it/s]
evelyn777-chai-sft-3b-v5-v1-uploader: Downloaded in 4.348s
evelyn777-chai-sft-3b-v5-v1-uploader: Processed model evelyn777/chai-sft-3b-v5 in 6.752s
evelyn777-chai-sft-3b-v5-v1-uploader: creating bucket guanaco-vllm-models
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v5-v1-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
evelyn777-chai-sft-3b-v5-v1-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v5-v1-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v5-v1-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v5-v1-uploader:   if re.search("-\.", bucket, re.UNICODE):
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
evelyn777-chai-sft-3b-v5-v1-uploader:   if re.search("\.\.", bucket, re.UNICODE):
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
evelyn777-chai-sft-3b-v5-v1-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
evelyn777-chai-sft-3b-v5-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
evelyn777-chai-sft-3b-v5-v1-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
evelyn777-chai-sft-3b-v5-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
evelyn777-chai-sft-3b-v5-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v5-v1
evelyn777-chai-sft-3b-v5-v1-uploader: cp /dev/shm/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v5-v1/model-00002-of-00002.safetensors
evelyn777-chai-sft-3b-v5-v1-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v5-v1/model-00001-of-00002.safetensors
Job evelyn777-chai-sft-3b-v5-v1-uploader completed after 82.83s with status: succeeded
Stopping job with name evelyn777-chai-sft-3b-v5-v1-uploader
Pipeline stage VLLMUploader completed in 83.37s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service evelyn777-chai-sft-3b-v5-v1
Waiting for inference service evelyn777-chai-sft-3b-v5-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Tearing down inference service evelyn777-chai-sft-3b-v5-v1
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService evelyn777-chai-sft-3b-v5-v1.                                The InferenceService is as following: {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'kind\': \'InferenceService\', \'metadata\': {\'annotations\': {\'autoscaling.knative.dev/class\': \'hpa.autoscaling.knative.dev\', \'autoscaling.knative.dev/container-concurrency-target-percentage\': \'70\', \'autoscaling.knative.dev/initial-scale\': \'5\', \'autoscaling.knative.dev/max-scale-down-rate\': \'1.1\', \'autoscaling.knative.dev/max-scale-up-rate\': \'2\', \'autoscaling.knative.dev/metric\': \'mean_pod_latency_ms_v2\', \'autoscaling.knative.dev/panic-threshold-percentage\': \'650\', \'autoscaling.knative.dev/panic-window-percentage\': \'35\', \'autoscaling.knative.dev/scale-down-delay\': \'30s\', \'autoscaling.knative.dev/scale-to-zero-grace-period\': \'10m\', \'autoscaling.knative.dev/stable-window\': \'180s\', \'autoscaling.knative.dev/target\': \'4000\', \'autoscaling.knative.dev/target-burst-capacity\': \'-1\', \'autoscaling.knative.dev/tick-interval\': \'15s\', \'features.knative.dev/http-full-duplex\': \'Enabled\', \'networking.knative.dev/ingress-class\': \'istio.ingress.networking.knative.dev\', \'serving.knative.dev/progress-deadline\': \'20m\'}, \'creationTimestamp\': \'2026-02-08T07:45:34Z\', \'finalizers\': [\'inferenceservice.finalizers\'], \'generation\': 1, \'labels\': {\'knative.coreweave.cloud/ingress\': \'istio.ingress.networking.knative.dev\', \'prometheus.k.chaiverse.com\': \'true\', \'qos.coreweave.cloud/latency\': \'low\'}, \'managedFields\': [{\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:annotations\': {\'.\': {}, \'f:autoscaling.knative.dev/class\': {}, \'f:autoscaling.knative.dev/container-concurrency-target-percentage\': {}, \'f:autoscaling.knative.dev/initial-scale\': {}, \'f:autoscaling.knative.dev/max-scale-down-rate\': {}, \'f:autoscaling.knative.dev/max-scale-up-rate\': {}, \'f:autoscaling.knative.dev/metric\': {}, \'f:autoscaling.knative.dev/panic-threshold-percentage\': {}, \'f:autoscaling.knative.dev/panic-window-percentage\': {}, \'f:autoscaling.knative.dev/scale-down-delay\': {}, \'f:autoscaling.knative.dev/scale-to-zero-grace-period\': {}, \'f:autoscaling.knative.dev/stable-window\': {}, \'f:autoscaling.knative.dev/target\': {}, \'f:autoscaling.knative.dev/target-burst-capacity\': {}, \'f:autoscaling.knative.dev/tick-interval\': {}, \'f:features.knative.dev/http-full-duplex\': {}, \'f:networking.knative.dev/ingress-class\': {}, \'f:serving.knative.dev/progress-deadline\': {}}, \'f:labels\': {\'.\': {}, \'f:knative.coreweave.cloud/ingress\': {}, \'f:prometheus.k.chaiverse.com\': {}, \'f:qos.coreweave.cloud/latency\': {}}}, \'f:spec\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:affinity\': {\'.\': {}, \'f:nodeAffinity\': {\'.\': {}, \'f:tion\': {}, \'f:requiredDuringSchedulingIgnoredDuringExecution\': {}}}, \'f:containerConcurrency\': {}, \'f:containers\': {}, \'f:imagePullSecrets\': {}, \'f:maxReplicas\': {}, \'f:minReplicas\': {}, \'f:priorityClassName\': {}, \'f:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2026-02-08T07:45:34Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2026-02-08T07:45:34Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2026-02-08T07:45:35Z\'}], \'name\': \'evelyn777-chai-sft-3b-v5-v1\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'425964899\', \'uid\': \'5420d821-8000-44fa-929e-eee01faa65f8\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'args\': [\'serve\', \'s3://guanaco-vllm-models/evelyn777-chai-sft-3b-v5-v1\', \'--port\', \'8080\', \'--tensor-parallel-size\', \'1\', \'--max-model-len\', \'8192\', \'--max-num-batched-tokens\', \'8192\', \'--max-num-seqs\', \'64\', \'--load-format\', \'runai_streamer\', \'--served-model-name\', \'evelyn777/chai-sft-3b-v5\'], \'env\': [{\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'VLLM_ASSETS_CACHE\', \'value\': \'/code/vllm_assets_cache\'}, {\'name\': \'RUNAI_STREAMER_S3_USE_VIRTUAL_ADDRESSING\', \'value\': \'0\'}, {\'name\': \'RUNAI_STREAMER_CONCURRENCY\', \'value\': \'1\'}, {\'name\': \'AWS_EC2_METADATA_DISABLED\', \'value\': \'true\'}, {\'name\': \'AWS_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'AWS_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'AWS_ENDPOINT_URL\', \'value\': \'http://s3-proxy.storage-system.svc.cluster.local:8080\'}, {\'name\': \'HF_TOKEN\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'token\', \'name\': \'hf-token\'}}}], \'image\': \'gcr.io/chai-959f8/vllm:v0.13.0\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'failureThreshold\': 1, \'httpGet\': {\'path\': \'/v1/models\', \'port\': 8080}, \'initialDelaySeconds\': 60, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'64Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'64Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}, {\'mountPath\': \'/root/.cache\', \'name\': \'cache-volume\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 40, \'minReplicas\': 0, \'priorityClassName\': \'creator-studio\', \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\', \'sizeLimit\': \'64Gi\'}, \'name\': \'shared-memory-cache\'}, {\'name\': \'cache-volume\', \'persistentVolumeClaim\': {\'claimName\': \'cache-pvc\'}}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'evelyn777-chai-sft-3b-v5-v1-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'message\': \'Revision "evelyn777-chai-sft-3b-v5-v1-predictor-00001" failed with message: 0/77 nodes are available: 1 node(s) were unschedulable, 10 Insufficient nvidia.com/gpu, 66 node(s) didn\\\'t match Pod\\\'s node affinity/selector. no new claims to deallocate, preemption: 0/77 nodes are available: 10 Insufficient nvidia.com/gpu, 67 Preemption is not helpful for scheduling..\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'message\': \'Configuration "evelyn777-chai-sft-3b-v5-v1-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'message\': \'Configuration "evelyn777-chai-sft-3b-v5-v1-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'message\': \'Configuration "evelyn777-chai-sft-3b-v5-v1-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2026-02-08T07:45:35Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'states\': {\'activeModelState\': \'\', \'targetModelState\': \'Pending\'}, \'transitionStatus\': \'InProgress\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage VLLMDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage VLLMDeleter completed in 0.18s
run pipeline stage %s
Running pipeline stage VLLMModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key evelyn777-chai-sft-3b-v5-v1/.gitattributes from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/added_tokens.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/chat_template.jinja from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/config.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/generation_config.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/merges.txt from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/model-00001-of-00002.safetensors from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/model-00002-of-00002.safetensors from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/model.safetensors.index.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/special_tokens_map.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/tokenizer.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/tokenizer_config.json from bucket guanaco-vllm-models
Deleting key evelyn777-chai-sft-3b-v5-v1/vocab.json from bucket guanaco-vllm-models
Pipeline stage VLLMModelDeleter completed in 3.12s
Shutdown handler de-registered
evelyn777-chai-sft-3b-v5_v1 status is now failed due to DeploymentManager action