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-v3-mkmlizer
Waiting for job on chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer to finish
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ║                                                                     ║
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: Downloaded to shared memory in 26.886s
chaiml-0sw-96p-4ff-chai-45017-v3-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-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcecfvl1a, device:0
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/flywheel_model.2.safetensors
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/flywheel_model.0.safetensors
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/flywheel_model.1.safetensors
chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer: 
Loading 0:   0%|          | 0/243 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/243 [00:00<00:21, 11.08it/s]
Loading 0:   4%|▍         | 10/243 [00:00<00:05, 38.87it/s]
Loading 0:   7%|▋         | 17/243 [00:00<00:05, 44.98it/s]
Loading 0:  11%|█         | 26/243 [00:00<00:03, 58.67it/s]
Loading 0:  14%|█▍        | 34/243 [00:00<00:03, 62.26it/s]
Loading 0:  17%|█▋        | 41/243 [00:00<00:03, 58.31it/s]
Loading 0:  21%|██        | 50/243 [00:00<00:02, 66.54it/s]
Loading 0:  24%|██▍       | 58/243 [00:00<00:02, 68.28it/s]
Loading 0:  27%|██▋       | 66/243 [00:01<00:02, 64.57it/s]
Loading 0:  30%|███       | 74/243 [00:01<00:02, 68.21it/s]
Loading 0:  34%|███▎      | 82/243 [00:01<00:02, 69.18it/s]
Loading 0:  36%|███▌      | 88/243 [00:16<00:02, 69.18it/s]
Loading 0:  37%|███▋      | 89/243 [00:16<01:34,  1.63it/s]
Loading 0:  41%|████      | 100/243 [00:16<00:54,  2.62it/s]
Loading 0:  44%|████▍     | 108/243 [00:16<00:37,  3.61it/s]
Loading 0:  49%|████▊     | 118/243 [00:16<00:23,  5.33it/s]
Loading 0:  52%|█████▏    | 126/243 [00:17<00:16,  7.17it/s]
Loading 0:  56%|█████▌    | 136/243 [00:17<00:10, 10.31it/s]
Loading 0:  59%|█████▉    | 144/243 [00:17<00:07, 13.45it/s]
Loading 0:  63%|██████▎   | 154/243 [00:17<00:04, 18.67it/s]
Loading 0:  67%|██████▋   | 162/243 [00:17<00:03, 23.30it/s]
Loading 0:  71%|███████   | 172/243 [00:17<00:02, 30.79it/s]
Loading 0:  74%|███████▍  | 181/243 [00:17<00:01, 37.18it/s]
Loading 0:  78%|███████▊  | 190/243 [00:17<00:01, 44.69it/s]
Loading 0:  82%|████████▏ | 199/243 [00:17<00:00, 50.59it/s]
Loading 0:  84%|████████▍ | 205/243 [00:33<00:00, 50.59it/s]
Loading 0:  85%|████████▍ | 206/243 [00:33<00:20,  1.78it/s]
Loading 0:  88%|████████▊ | 214/243 [00:33<00:11,  2.48it/s]
Loading 0:  91%|█████████▏| 222/243 [00:33<00:06,  3.46it/s]
Loading 0:  95%|█████████▌| 232/243 [00:33<00:02,  5.15it/s]
Loading 0:  99%|█████████▉| 240/243 [00:33<00:00,  6.96it/s]
                                                            
Job chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer completed after 105.83s with status: succeeded
Stopping job with name chaiml-0sw-96p-4ff-chai-45017-v3-mkmlizer
Pipeline stage MKMLizer completed in 106.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3 to be ready
Inference service chaiml-0sw-96p-4ff-chai-45017-v3 ready after 241.62956023216248s
Pipeline stage MKMLDeployer completed in 242.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.100757122039795s
Received healthy response to inference request in 1.5039417743682861s
Received healthy response to inference request in 1.718806505203247s
Received healthy response to inference request in 1.543806552886963s
Received healthy response to inference request in 1.4785833358764648s
5 requests
0 failed requests
5th percentile: 1.4836550235748291
10th percentile: 1.4887267112731934
20th percentile: 1.4988700866699218
30th percentile: 1.5119147300720215
40th percentile: 1.5278606414794922
50th percentile: 1.543806552886963
60th percentile: 1.6138065338134766
70th percentile: 1.68380651473999
80th percentile: 1.7951966285705567
90th percentile: 1.9479768753051758
95th percentile: 2.0243669986724853
99th percentile: 2.085479097366333
mean time: 1.6691790580749513
Pipeline stage StressChecker completed in 9.74s
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 0.72s
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 0.97s
Shutdown handler de-registered
chaiml-0sw-96p-4ff-chai_45017_v3 status is now deployed due to DeploymentManager action
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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v3-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\': \'2025-06-25T01:17:57Z\', \'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\': \'2025-06-25T01:17:57Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T01:17:57Z\'}, {\'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\': \'2025-06-25T01:27:59Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v3-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435491169\', \'uid\': \'fc711c94-fc86-4098-8c63-2e3d4a06e1e3\'}, \'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-v3\'}, {\'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-v3-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T01:18:48Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:27:59Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor-00001" failed with message: Container failed with: 0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.53.122\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m22.336s\\nuser\\t0m7.116s\\nsys\\t0m37.843s\\nstart_server.sh: line 23:    94 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:18:48Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:18:48Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:18:48Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T01:18:48Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.53.122\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m22.336s\\nuser\\t0m7.116s\\nsys\\t0m37.843s\\nstart_server.sh: line 23:    94 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 0.14s
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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v3-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\': \'2025-06-25T01:49:16Z\', \'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\': \'2025-06-25T01:49:16Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T01:49:16Z\'}, {\'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\': \'2025-06-25T01:59:20Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v3-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435519711\', \'uid\': \'a688bc1d-bd9e-4f9f-adf1-7b0ee854f90a\'}, \'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-v3\'}, {\'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-v3-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T01:50:52Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:59:20Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor-00001" failed with message: Container failed with: 0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.53.101\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m22.556s\\nuser\\t0m7.049s\\nsys\\t0m38.254s\\nstart_server.sh: line 23:    91 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:50:52Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:50:52Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T01:50:52Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T01:50:52Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.53.101\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m22.556s\\nuser\\t0m7.049s\\nsys\\t0m38.254s\\nstart_server.sh: line 23:    91 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
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 0.18s
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-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
Waiting for inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler to be ready
Tearing down inference service chaiml-0sw-96p-4ff-chai-45017-v3-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-0sw-96p-4ff-chai-45017-v3-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\': \'2025-06-25T02:20:46Z\', \'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\': \'2025-06-25T02:20:46Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:20:46Z\'}, {\'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\': \'2025-06-25T02:30:48Z\'}], \'name\': \'chaiml-0sw-96p-4ff-chai-45017-v3-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435549772\', \'uid\': \'944a7556-e818-41de-b8fb-e23a4c62bbb8\'}, \'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-v3\'}, {\'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-v3-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T02:22:21Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:30:48Z\', \'message\': \'Revision "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor-00001" failed with message: Container failed with: e0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.55.67\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m20.620s\\nuser\\t0m5.950s\\nsys\\t0m33.946s\\nstart_server.sh: line 23:    92 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:22:21Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:22:21Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:22:21Z\', \'message\': \'Configuration "chaiml-0sw-96p-4ff-chai-45017-v3-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T02:22:21Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'e0 CPU(s):                  0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\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: 216.153.55.67\\ndownloading s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-0sw-96p-4ff-chai-45017-v3/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\\t0m20.620s\\nuser\\t0m5.950s\\nsys\\t0m33.946s\\nstart_server.sh: line 23:    92 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_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now protected due to ABTestQueueItem
chaiml-0sw-96p-4ff-chai_45017_v3 status is now inactive
chaiml-0sw-96p-4ff-chai_45017_v3 status is now torndown due to DeploymentManager action