Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer
Waiting for job on chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer to finish
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: Downloaded to shared memory in 28.761s
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: Checking if ChaiML/0sw_96p_4ff_chaiml_snugstable1_5_1_59274_v21_merge_s0_to_w0 already exists in ChaiML
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp48_vpm9z, device:0
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: quantized model in 41.810s
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: Processed model ChaiML/0sw_96p_4ff_chaiml_snugstable1_5_1_59274_v21_merge_s0_to_w0 in 70.583s
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.0.safetensors
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.1.safetensors
chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer: 
Loading 0:   0%|          | 0/243 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/243 [00:00<00:22, 10.50it/s]
Loading 0:   4%|▍         | 10/243 [00:00<00:06, 37.03it/s]
Loading 0:   7%|▋         | 17/243 [00:00<00:05, 43.21it/s]
Loading 0:  11%|█         | 26/243 [00:00<00:03, 56.83it/s]
Loading 0:  14%|█▍        | 34/243 [00:00<00:03, 61.05it/s]
Loading 0:  17%|█▋        | 41/243 [00:00<00:03, 57.68it/s]
Loading 0:  21%|██        | 50/243 [00:00<00:02, 66.04it/s]
Loading 0:  24%|██▍       | 58/243 [00:01<00:02, 67.88it/s]
Loading 0:  27%|██▋       | 66/243 [00:01<00:02, 64.35it/s]
Loading 0:  30%|███       | 74/243 [00:01<00:02, 67.99it/s]
Loading 0:  34%|███▎      | 82/243 [00:01<00:02, 69.29it/s]
Loading 0:  36%|███▌      | 88/243 [00:11<00:02, 69.29it/s]
Loading 0:  37%|███▋      | 89/243 [00:17<01:38,  1.56it/s]
Loading 0:  41%|████      | 100/243 [00:17<00:56,  2.51it/s]
Loading 0:  44%|████▍     | 108/243 [00:17<00:39,  3.46it/s]
Loading 0:  49%|████▊     | 118/243 [00:17<00:24,  5.11it/s]
Loading 0:  52%|█████▏    | 126/243 [00:17<00:17,  6.87it/s]
Loading 0:  56%|█████▌    | 136/243 [00:17<00:10,  9.88it/s]
Loading 0:  59%|█████▉    | 144/243 [00:17<00:07, 12.89it/s]
Loading 0:  63%|██████▎   | 154/243 [00:18<00:04, 17.91it/s]
Loading 0:  67%|██████▋   | 162/243 [00:18<00:03, 22.34it/s]
Loading 0:  71%|███████   | 172/243 [00:18<00:02, 29.46it/s]
Loading 0:  74%|███████▍  | 180/243 [00:18<00:01, 34.66it/s]
Loading 0:  78%|███████▊  | 190/243 [00:18<00:01, 43.11it/s]
Loading 0:  81%|████████▏ | 198/243 [00:18<00:00, 47.62it/s]
Loading 0:  84%|████████▍ | 205/243 [00:30<00:00, 47.62it/s]
Loading 0:  85%|████████▍ | 206/243 [00:34<00:21,  1.73it/s]
Loading 0:  88%|████████▊ | 214/243 [00:34<00:12,  2.40it/s]
Loading 0:  91%|█████████▏| 222/243 [00:35<00:06,  3.33it/s]
Loading 0:  95%|█████████▌| 232/243 [00:35<00:02,  4.95it/s]
Loading 0:  99%|█████████▉| 240/243 [00:35<00:00,  6.68it/s]
                                                            
Job chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer completed after 104.6s with status: succeeded
Stopping job with name chaiml-0sw-96p-4ff-chai-45017-v4-mkmlizer
Pipeline stage MKMLizer completed in 105.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4 to be ready
Inference service chaiml-0sw-96p-4ff-chai-45017-v4 ready after 230.77694869041443s
Pipeline stage MKMLDeployer completed in 231.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.112854480743408s
Received healthy response to inference request in 1.8091557025909424s
Received healthy response to inference request in 1.310368537902832s
Received healthy response to inference request in 1.37809419631958s
Received healthy response to inference request in 1.3700745105743408s
5 requests
0 failed requests
5th percentile: 1.3223097324371338
10th percentile: 1.3342509269714355
20th percentile: 1.358133316040039
30th percentile: 1.3716784477233888
40th percentile: 1.3748863220214844
50th percentile: 1.37809419631958
60th percentile: 1.550518798828125
70th percentile: 1.7229434013366698
80th percentile: 1.8698954582214355
90th percentile: 1.9913749694824219
95th percentile: 2.052114725112915
99th percentile: 2.1007065296173097
mean time: 1.5961094856262208
Pipeline stage StressChecker completed in 9.16s
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 0.60s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.70s
Shutdown handler de-registered
chaiml-0sw-96p-4ff-chai_45017_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v4-profiler.                                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\': \'1\', \'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\'}, \'creationTimestamp\': \'2025-06-25T02:24:32Z\', \'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: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:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:24:32Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:24:32Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:lastFailureInfo\': {\'.\': {}, \'f:exitCode\': {}, \'f:message\': {}, \'f:reason\': {}}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-06-25T02:34:34Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435553048\', \'uid\': \'924a5bd4-94ac-470d-8d77-8e9d231ae984\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1024\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'TOP_P\', \'value\': \'1.0\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "####", "You:", "<|eot_id|>", "</s>", "Bot:", "<|im_end|>", "User:"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'s0\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:q4_flywheel_0293\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T02:26:07Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:34:34Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001" failed with message: Container failed with: tances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-47\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.53.112\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m15.104s\\nuser\\t0m5.904s\\nsys\\t0m24.187s\\nstart_server.sh: line 23:    85 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:26:07Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:26:07Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:26:07Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T02:26:07Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'tances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-47\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.53.112\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m15.104s\\nuser\\t0m5.904s\\nsys\\t0m24.187s\\nstart_server.sh: line 23:    85 Killed                  python3 main.py\\n\', \'reason\': \'ModelLoadFailed\'}, \'states\': {\'activeModelState\': \'\', \'targetModelState\': \'FailedToLoad\'}, \'transitionStatus\': \'BlockedByFailedLoad\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.22s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v4-profiler.                                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\': \'1\', \'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\'}, \'creationTimestamp\': \'2025-06-25T02:56:12Z\', \'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: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:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:56:12Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:56:12Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:lastFailureInfo\': {\'.\': {}, \'f:exitCode\': {}, \'f:message\': {}, \'f:reason\': {}}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-06-25T03:06:14Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435581958\', \'uid\': \'e726474e-63a0-4b3b-a1ad-7f04dbf24656\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1024\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'TOP_P\', \'value\': \'1.0\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "####", "You:", "<|eot_id|>", "</s>", "Bot:", "<|im_end|>", "User:"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'s0\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:q4_flywheel_0293\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T02:57:39Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:06:14Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001" failed with message: Container failed with: tances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-47\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.53.119\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m16.164s\\nuser\\t0m6.775s\\nsys\\t0m25.628s\\nstart_server.sh: line 23:    88 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:57:39Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:57:39Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:57:39Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T02:57:39Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'tances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-47\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.53.119\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m16.164s\\nuser\\t0m6.775s\\nsys\\t0m25.628s\\nstart_server.sh: line 23:    88 Killed                  python3 main.py\\n\', \'reason\': \'ModelLoadFailed\'}, \'states\': {\'activeModelState\': \'\', \'targetModelState\': \'FailedToLoad\'}, \'transitionStatus\': \'BlockedByFailedLoad\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.18s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v4-profiler.                                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\': \'1\', \'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\'}, \'creationTimestamp\': \'2025-06-25T03:27:34Z\', \'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: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:timeout\': {}, \'f:volumes\': {}}}}, \'manager\': \'OpenAPI-Generator\', \'operation\': \'Update\', \'time\': \'2025-06-25T03:27:34Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T03:27:34Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:status\': {\'.\': {}, \'f:components\': {\'.\': {}, \'f:predictor\': {\'.\': {}, \'f:latestCreatedRevision\': {}}}, \'f:conditions\': {}, \'f:modelStatus\': {\'.\': {}, \'f:lastFailureInfo\': {\'.\': {}, \'f:exitCode\': {}, \'f:message\': {}, \'f:reason\': {}}, \'f:states\': {\'.\': {}, \'f:activeModelState\': {}, \'f:targetModelState\': {}}, \'f:transitionStatus\': {}}, \'f:observedGeneration\': {}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'subresource\': \'status\', \'time\': \'2025-06-25T03:37:35Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435624021\', \'uid\': \'05c4894b-f114-4419-baa4-ee598408d8e5\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'RTX_A5000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'1024\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.0\'}, {\'name\': \'TOP_P\', \'value\': \'1.0\'}, {\'name\': \'MIN_P\', \'value\': \'0.05\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "####", "You:", "<|eot_id|>", "</s>", "Bot:", "<|im_end|>", "User:"]\'}, {\'name\': \'MAX_TOKENS\', \'value\': \'64\'}, {\'name\': \'MAX_BATCH_SIZE\', \'value\': \'128\'}, {\'name\': \'MAX_CACHED_RESPONSES\', \'value\': \'-1\'}, {\'name\': \'URL_ROUTE\', \'value\': \'GPT-J-6B-lit-v2\'}, {\'name\': \'OBJ_ACCESS_KEY_ID\', \'value\': \'LETMTTRMLFFAMTBK\'}, {\'name\': \'OBJ_SECRET_ACCESS_KEY\', \'value\': \'VwwZaqefOOoaouNxUk03oUmK9pVEfruJhjBHPGdgycK\'}, {\'name\': \'OBJ_ENDPOINT\', \'value\': \'https://accel-object.ord1.coreweave.com\'}, {\'name\': \'TENSORIZER_URI\', \'value\': \'s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4\'}, {\'name\': \'RESERVE_MEMORY\', \'value\': \'2048\'}, {\'name\': \'DOWNLOAD_TO_LOCAL\', \'value\': \'/dev/shm/model_cache\'}, {\'name\': \'NUM_GPUS\', \'value\': \'1\'}, {\'name\': \'MK1_QUANTIZATION_PROFILE\', \'value\': \'s0\'}, {\'name\': \'MK1_MKML_LICENSE_KEY\', \'valueFrom\': {\'secretKeyRef\': {\'key\': \'key\', \'name\': \'mkml-license-key\'}}}], \'image\': \'gcr.io/chai-959f8/chai-guanaco/mkml:q4_flywheel_0293\', \'imagePullPolicy\': \'IfNotPresent\', \'name\': \'kserve-container\', \'readinessProbe\': {\'exec\': {\'command\': [\'cat\', \'/tmp/ready\']}, \'failureThreshold\': 1, \'initialDelaySeconds\': 10, \'periodSeconds\': 10, \'successThreshold\': 1, \'timeoutSeconds\': 5}, \'resources\': {\'limits\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'14Gi\', \'nvidia.com/gpu\': \'1\'}}, \'volumeMounts\': [{\'mountPath\': \'/dev/shm\', \'name\': \'shared-memory-cache\'}]}], \'imagePullSecrets\': [{\'name\': \'docker-creds\'}], \'maxReplicas\': 1, \'minReplicas\': 1, \'timeout\': 60, \'volumes\': [{\'emptyDir\': {\'medium\': \'Memory\'}, \'name\': \'shared-memory-cache\'}]}}, \'status\': {\'components\': {\'predictor\': {\'latestCreatedRevision\': \'chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T03:29:06Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:37:35Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor-00001" failed with message: Container failed with: stances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-63\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.56.66\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m16.137s\\nuser\\t0m4.818s\\nsys\\t0m27.165s\\nstart_server.sh: line 23:    82 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:29:06Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:29:06Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:29:06Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T03:29:06Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'stances)\\nNUMA node(s):                       1\\nNUMA node0 CPU(s):                  0-63\\nVulnerability Gather data sampling: Not affected\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Not affected\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode\\nVulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl\\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\\nVulnerability Spectre v2:           Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 24564 MiB, NVIDIA RTX A5000\\nIP: 216.153.56.66\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v4/flywheel_model.2.safetensors /dev/shm/model_cache/flywheel_model.2.safetensors\\nstart_server.sh: line 20:    44 Killed                  s5cmd --log debug --credentials-file uploading/s5cfg --endpoint-url https://object.ord1.coreweave.com cp --concurrency 4 "$TENSORIZER_URI/*" $DOWNLOAD_TO_LOCAL\\n\\nreal\\t0m16.137s\\nuser\\t0m4.818s\\nsys\\t0m27.165s\\nstart_server.sh: line 23:    82 Killed                  python3 main.py\\n\', \'reason\': \'ModelLoadFailed\'}, \'states\': {\'activeModelState\': \'\', \'targetModelState\': \'FailedToLoad\'}, \'transitionStatus\': \'BlockedByFailedLoad\'}, \'observedGeneration\': 1}}')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.19s
Shutdown handler de-registered
chaiml-0sw-96p-4ff-chai_45017_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-0sw-96p-4ff-chai_45017_v4 status is now torndown due to DeploymentManager action