chaiml-merged-qwen-35-_39140

submission_id: chaiml-merged-qwen-35-_39140_v18
developer_uid: Meliodia
status: torndown
model_repo: ChaiML/merged_qwen_35_dpo_lower_lr_v
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '<|im_start|>', '###', '</s>', '<|im_end|>'], 'max_input_tokens': 2048, 'best_of': 1, 'max_output_tokens': 80}
formatter: {'memory_template': '<|im_start|>system\nRespond as a high quality storyteller.<|im_end|>\n<|im_start|>user\n', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '<|im_end|>\n<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
timestamp: 2026-03-28T16:56:20+00:00
model_name: chaiml-merged-qwen-35-_39140_v17
Resubmit model
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-v18-uploader
Waiting for job on chaiml-merged-qwen-35-39140-v18-uploader to finish
Failed to get response for submission chaiml-glm-47-bobo-v1-s_46691_v1: HTTPConnectionPool(host='chaiml-glm-47-bobo-v1-s-46691-v1-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=20.0)
2026-03-28T16:13:54.458279+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
chaiml-merged-qwen-35-39140-v18-uploader: Using quantization_mode: fp8
chaiml-merged-qwen-35-39140-v18-uploader: Checking if ChaiML/merged_qwen_35_dpo_lower_lr_v-FP8 already exists in ChaiML
chaiml-merged-qwen-35-39140-v18-uploader: Model already exists. Downloading to /dev/shm/model_output...
chaiml-merged-qwen-35-39140-v18-uploader: Downloading snapshot of ChaiML/merged_qwen_35_dpo_lower_lr_v-FP8...
chaiml-merged-qwen-35-39140-v18-uploader: Downloaded in 30.980s
chaiml-merged-qwen-35-39140-v18-uploader: Processed model ChaiML/merged_qwen_35_dpo_lower_lr_v in 33.820s
chaiml-merged-qwen-35-39140-v18-uploader: creating bucket guanaco-vllm-models
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v18-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-merged-qwen-35-39140-v18-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v18-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v18-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v18-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-merged-qwen-35-39140-v18-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-merged-qwen-35-39140-v18-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-merged-qwen-35-39140-v18-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-merged-qwen-35-39140-v18-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-merged-qwen-35-39140-v18-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-merged-qwen-35-39140-v18-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/.gitattributes
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/generation_config.json
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/recipe.yaml s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/recipe.yaml
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/config.json
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/chat_template.jinja
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/tokenizer_config.json
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/tokenizer.json
2026-03-28T16:14:54.546880+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
chaiml-merged-qwen-35-39140-v18-uploader: cp /dev/shm/model_output/model.safetensors s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default/model.safetensors
Job chaiml-merged-qwen-35-39140-v18-uploader completed after 173.45s with status: succeeded
Stopping job with name chaiml-merged-qwen-35-39140-v18-uploader
Pipeline stage VLLMUploader completed in 173.88s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.10s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.66s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-merged-qwen-35-39140-v18
Waiting for inference service chaiml-merged-qwen-35-39140-v18 to be ready
2026-03-28T16:15:54.643416+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:16:54.746435+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:17:54.842079+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:18:54.936336+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:19:55.025442+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:20:55.114350+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:21:55.214924+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:22:55.313070+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:23:55.410571+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:24:55.514267+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:25:55.606258+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:26:55.701387+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:27:55.799219+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:28:55.926855+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:29:56.028370+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:30:56.124547+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:31:56.254574+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:32:56.353275+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:33:56.444183+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:34:56.540934+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:35:56.647319+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
Failed to get request counts for guanaco-submitter. Falling back to default
2026-03-28T16:36:56.742579+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:37:56.839758+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:38:56.932874+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:39:57.034055+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:40:57.131226+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:41:57.224048+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:42:57.316083+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:43:57.413528+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:44:57.508796+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:45:57.607939+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:46:57.705259+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:47:57.798927+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:48:57.894222+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:49:57.992470+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:50:58.089207+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
Failed to get response for submission chaiml-gspo-glm47-combi_10268_v1: ('http://chaiml-gspo-glm47-combi-10268-v1-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/completions', 'activator request timeout')
2026-03-28T16:51:58.181010+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:52:58.269729+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:53:58.387667+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
2026-03-28T16:54:58.474521+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
Tearing down inference service chaiml-merged-qwen-35-39140-v18
2026-03-28T16:55:58.572863+00:00 monitor updated for chaiml-merged-qwen-35-_39140_v18
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-merged-qwen-35-39140-v18.                                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\': \'40m\'}, \'creationTimestamp\': \'2026-03-28T16:15:51Z\', \'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:podAffinity\': {\'.\': {}, \'f:tion\': {}}}, \'f:containerConcurrency\': {}, \'f:containers\': {}, \'f:imagePullSecrets\': {}, \'f:maxReplicas\': {}, \'f:minReplicas\': {}, \'f:priorityClassName\': {}, \'f:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2026-03-28T16:15:51Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2026-03-28T16:15:51Z\'}, {\'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\': \'2026-03-28T16:18:34Z\'}], \'name\': \'chaiml-merged-qwen-35-39140-v18\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'557022188\', \'uid\': \'6923480e-69a6-4eb5-bf06-78dbba4bed47\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'L40S\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'L40S\']}]}]}}, \'podAffinity\': {\'tion\': [{\'podAffinityTerm\': {\'labelSelector\': {\'matchLabels\': {\'serving.kserve.io/inferenceservice\': \'chaiml-merged-qwen-35-39140-v18\'}}, \'topologyKey\': \'kubernetes.io/hostname\'}, \'weight\': 100}]}}, \'containerConcurrency\': 0, \'containers\': [{\'args\': [\'serve\', \'s3://guanaco-vllm-models/chaiml-merged-qwen-35-39140-v18/default\', \'--port\', \'8080\', \'--tensor-parallel-size\', \'1\', \'--max-model-len\', \'10240\', \'--max-num-batched-tokens\', \'10240\', \'--max-num-seqs\', \'64\', \'--load-format\', \'runai_streamer\', \'--served-model-name\', \'ChaiML/merged_qwen_35_dpo_lower_lr_v\', \'--model-loader-extra-config\', \'{"distributed": true, "concurrency": 2}\'], \'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\': \'1\'}, {\'name\': \'RUNAI_STREAMER_CONCURRENCY\', \'value\': \'1\'}, {\'name\': \'AWS_EC2_METADATA_DISABLED\', \'value\': \'true\'}, {\'name\': \'AWS_ACCESS_KEY_ID\', \'value\': \'CWZAGMHZXKZRFGJK\'}, {\'name\': \'AWS_SECRET_ACCESS_KEY\', \'value\': \'cwoAeWzp46q4O0sTNXOEuZ1MvZzKEFlS9DtEhnTldKp\'}, {\'name\': \'AWS_ENDPOINT_URL\', \'value\': \'https://cwobject.com\'}, {\'name\': \'HF_TOKEN\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'token\', \'name\': \'hf-token\'}}}], \'image\': \'gcr.io/chai-959f8/vllm:v0.17.1.transformers-5.3.0-dsa_patch\', \'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\': \'67Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'67Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 40, \'minReplicas\': 0, \'priorityClassName\': \'chaiverse\', \'timeout\': 20, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\', \'sizeLimit\': \'67Gi\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-merged-qwen-35-39140-v18-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2026-03-28T16:15:52Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2026-03-28T16:18:34Z\', \'message\': \'Revision "chaiml-merged-qwen-35-39140-v18-predictor-00001" failed with message: Container failed with:            ^^^^^^^^^^^^^^^^^^^^^\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/vllm/transformers_utils/processor.py", line 164, in get_processor\\n(APIServer pid=1)     processor = processor_cls.from_pretrained(\\n(APIServer pid=1)                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/processing_utils.py", line 1403, in from_pretrained\\n(APIServer pid=1)     args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, processor_dict, **kwargs)\\n(APIServer pid=1)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/processing_utils.py", line 1524, in _get_arguments_from_pretrained\\n(APIServer pid=1)     sub_processor = auto_processor_class.from_pretrained(\\n(APIServer pid=1)                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/models/auto/image_processing_auto.py", line 519, in from_pretrained\\n(APIServer pid=1)     raise initial_exception\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/models/auto/image_processing_auto.py", line 501, in from_pretrained\\n(APIServer pid=1)     config_dict, _ = ImageProcessingMixin.get_image_processor_dict(\\n(APIServer pid=1)                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n(APIServer pid=1)   File "/usr/local/lib/python3.12/dist-packages/transformers/image_processing_base.py", line 334, in get_image_processor_dict\\n(APIServer pid=1)     raise OSError(\\n(APIServer pid=1) OSError: Can\\\'t load image processor for \\\'/code/vllm_assets_cache/model_streamer/c4e95836\\\'. If you were trying to load it from \\\'https://huggingface.co/models\\\', make sure you don\\\'t have a local directory with the same name. Otherwise, make sure \\\'/code/vllm_assets_cache/model_streamer/c4e95836\\\' is the correct path to a directory containing a preprocessor_config.json file\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2026-03-28T16:15:52Z\', \'message\': \'Configuration "chaiml-merged-qwen-35-39140-v18-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2026-03-28T16:15:52Z\', \'message\': \'Configuration "chaiml-merged-qwen-35-39140-v18-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2026-03-28T16:15:52Z\', \'message\': \'Configuration "chaiml-merged-qwen-35-39140-v18-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2026-03-28T16:15:52Z\', \'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
Checking if service chaiml-merged-qwen-35-39140-v18 is running
Skipping teardown as no inference service was found
Pipeline stage VLLMDeleter completed in 0.37s
run pipeline stage %s
Running pipeline stage VLLMModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-merged-qwen-35-39140-v18/default/.gitattributes from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/chat_template.jinja from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/config.json from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/generation_config.json from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/model.safetensors from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/recipe.yaml from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/tokenizer.json from bucket guanaco-vllm-models
Deleting key chaiml-merged-qwen-35-39140-v18/default/tokenizer_config.json from bucket guanaco-vllm-models
Pipeline stage VLLMModelDeleter completed in 3.73s
Shutdown handler de-registered
chaiml-merged-qwen-35-_39140_v18 status is now failed due to DeploymentManager action
admin requested tearing down of chaiml-merged-qwen-35-_39140_v18
Shutdown handler not registered because Python interpreter is not running in the main thread
chaiml-merged-qwen-35-_39140_v18 status is now torndown due to DeploymentManager action