developer_uid: richhx
submission_id: chaiml-mistral-24b-dpo-_59605_v4
model_name: chaiml-mistral-24b-dpo-_59605_v4
model_group: ChaiML/mistral_24b_dpo_4
status: torndown
timestamp: 2025-06-25T01:59:00+00:00
num_battles: 8041
num_wins: 3937
celo_rating: 1261.44
family_friendly_score: 0.5838
family_friendly_standard_error: 0.006971048127792549
submission_type: basic
model_repo: ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2_s0_to_w0
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: chaiml-mistral-24b-dpo-_59605_v4
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2_s0_to_w0
model_size: 24B
ranking_group: single
us_pacific_date: 2025-06-24
win_ratio: 0.48961571943788085
generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.6, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', 'You:', '</s>', '###'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '[INST]', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '[/INST]{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-mistral-24b-dpo-59605-v4-mkmlizer
Waiting for job on chaiml-mistral-24b-dpo-59605-v4-mkmlizer to finish
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: Downloaded to shared memory in 93.762s
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: Checking if ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2_s0_to_w0 already exists in ChaiML
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvyhdpi1y, device:0
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: quantized model in 76.028s
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: Processed model ChaiML/mistral_24b_dpo_40k_95w_pref_1250_instruct_dpo_2_v2_s0_to_w0 in 169.791s
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.0.safetensors
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.3.safetensors
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.2.safetensors
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.1.safetensors
chaiml-mistral-24b-dpo-59605-v4-mkmlizer: 
Loading 0:   0%|          | 0/243 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/243 [00:00<00:13, 17.56it/s]
Loading 0:   4%|▎         | 9/243 [00:00<00:08, 26.87it/s]
Loading 0:   6%|▌         | 15/243 [00:00<00:07, 30.16it/s]
Loading 0:   9%|▊         | 21/243 [00:00<00:07, 31.50it/s]
Loading 0:  11%|█         | 27/243 [00:00<00:06, 32.38it/s]
Loading 0:  14%|█▎        | 33/243 [00:01<00:06, 33.01it/s]
Loading 0:  16%|█▌        | 39/243 [00:01<00:06, 33.21it/s]
Loading 0:  19%|█▊        | 45/243 [00:01<00:05, 33.63it/s]
Loading 0:  21%|██        | 50/243 [00:16<00:05, 33.63it/s]
Loading 0:  21%|██        | 51/243 [00:16<02:40,  1.19it/s]
Loading 0:  23%|██▎       | 57/243 [00:17<01:48,  1.71it/s]
Loading 0:  26%|██▌       | 63/243 [00:17<01:14,  2.42it/s]
Loading 0:  28%|██▊       | 69/243 [00:17<00:51,  3.38it/s]
Loading 0:  31%|███       | 75/243 [00:17<00:36,  4.66it/s]
Loading 0:  33%|███▎      | 81/243 [00:17<00:25,  6.33it/s]
Loading 0:  36%|███▌      | 87/243 [00:17<00:18,  8.44it/s]
Loading 0:  38%|███▊      | 93/243 [00:18<00:13, 10.97it/s]
Loading 0:  41%|████      | 99/243 [00:18<00:10, 13.90it/s]
Loading 0:  43%|████▎     | 105/243 [00:18<00:08, 17.11it/s]
Loading 0:  44%|████▍     | 107/243 [00:33<00:07, 17.11it/s]
Loading 0:  44%|████▍     | 108/243 [00:33<02:10,  1.04it/s]
Loading 0:  46%|████▌     | 111/243 [00:34<01:42,  1.28it/s]
Loading 0:  48%|████▊     | 117/243 [00:34<01:03,  1.98it/s]
Loading 0:  51%|█████     | 123/243 [00:34<00:40,  2.93it/s]
Loading 0:  53%|█████▎    | 129/243 [00:34<00:27,  4.21it/s]
Loading 0:  56%|█████▌    | 135/243 [00:34<00:18,  5.88it/s]
Loading 0:  58%|█████▊    | 141/243 [00:34<00:12,  7.98it/s]
Loading 0:  60%|██████    | 147/243 [00:35<00:09, 10.55it/s]
Loading 0:  63%|██████▎   | 153/243 [00:35<00:06, 13.54it/s]
Loading 0:  66%|██████▌   | 160/243 [00:50<00:06, 13.54it/s]
Loading 0:  66%|██████▋   | 161/243 [00:50<01:02,  1.31it/s]
Loading 0:  69%|██████▊   | 167/243 [00:50<00:42,  1.80it/s]
Loading 0:  71%|███████   | 173/243 [00:51<00:28,  2.48it/s]
Loading 0:  74%|███████▎  | 179/243 [00:51<00:18,  3.41it/s]
Loading 0:  76%|███████▌  | 185/243 [00:51<00:12,  4.65it/s]
Loading 0:  79%|███████▊  | 191/243 [00:51<00:08,  6.26it/s]
Loading 0:  81%|████████  | 197/243 [00:51<00:05,  8.32it/s]
Loading 0:  84%|████████▍ | 204/243 [00:51<00:03, 11.36it/s]
Loading 0:  86%|████████▋ | 210/243 [00:52<00:02, 14.23it/s]
Loading 0:  89%|████████▉ | 216/243 [00:52<00:01, 17.39it/s]
Loading 0:  90%|████████▉ | 218/243 [01:07<00:01, 17.39it/s]
Loading 0:  90%|█████████ | 219/243 [01:07<00:22,  1.07it/s]
Loading 0:  91%|█████████▏| 222/243 [01:07<00:15,  1.32it/s]
Loading 0:  94%|█████████▍| 228/243 [01:07<00:07,  2.03it/s]
Loading 0:  96%|█████████▋| 234/243 [01:08<00:03,  2.99it/s]
Loading 0:  99%|█████████▉| 240/243 [01:08<00:00,  4.28it/s]
                                                            

Job chaiml-mistral-24b-dpo-59605-v4-mkmlizer completed after 215.98s with status: succeeded
Stopping job with name chaiml-mistral-24b-dpo-59605-v4-mkmlizer
Pipeline stage MKMLizer completed in 216.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-dpo-59605-v4
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4 to be ready
Inference service chaiml-mistral-24b-dpo-59605-v4 ready after 170.8437042236328s
Pipeline stage MKMLDeployer completed in 171.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.165682077407837s
Received healthy response to inference request in 1.8193395137786865s
Received healthy response to inference request in 1.3694071769714355s
Received healthy response to inference request in 1.6560633182525635s
Received healthy response to inference request in 1.3516738414764404s
5 requests
0 failed requests
5th percentile: 1.3552205085754394
10th percentile: 1.3587671756744384
20th percentile: 1.3658605098724366
30th percentile: 1.426738405227661
40th percentile: 1.5414008617401123
50th percentile: 1.6560633182525635
60th percentile: 1.7213737964630127
70th percentile: 1.786684274673462
80th percentile: 1.8886080265045166
90th percentile: 2.0271450519561767
95th percentile: 2.0964135646820066
99th percentile: 2.1518283748626708
mean time: 1.6724331855773926
Pipeline stage StressChecker completed in 9.95s
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 0.77s
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 0.79s
Shutdown handler de-registered
chaiml-mistral-24b-dpo-_59605_v4 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-mistral-24b-dpo-59605-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\': \'2025-06-25T02:26:53Z\', \'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\': \'2025-06-25T02:26:53Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:26:53Z\'}, {\'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\': \'2025-06-25T02:36:55Z\'}], \'name\': \'chaiml-mistral-24b-dpo-59605-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435555427\', \'uid\': \'aba89f3a-02c8-4a72-bf2a-4c89db6e887a\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'768\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'TOP_P\', \'value\': \'0.9\'}, {\'name\': \'MIN_P\', \'value\': \'0.6\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "</s>", "###", "You:"]\'}, {\'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-mistral-24b-dpo-59605-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\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'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-mistral-24b-dpo-59605-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T02:28:28Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:36:55Z\', \'message\': \'Revision "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor-00001" failed with message: Container failed with:    0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.68\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m28.463s\\nuser\\t0m8.371s\\nsys\\t0m46.567s\\nstart_server.sh: line 23:   115 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:28:28Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:28:28Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:28:28Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T02:28:28Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'   0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.68\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m28.463s\\nuser\\t0m8.371s\\nsys\\t0m46.567s\\nstart_server.sh: line 23:   115 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 0.15s
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 0.15s
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-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-mistral-24b-dpo-59605-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\': \'2025-06-25T02:58:14Z\', \'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\': \'2025-06-25T02:58:14Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T02:58:14Z\'}, {\'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\': \'2025-06-25T03:08:16Z\'}], \'name\': \'chaiml-mistral-24b-dpo-59605-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435583836\', \'uid\': \'1f50370b-1153-4904-bce1-98684e582bdf\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'768\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'TOP_P\', \'value\': \'0.9\'}, {\'name\': \'MIN_P\', \'value\': \'0.6\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "</s>", "###", "You:"]\'}, {\'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-mistral-24b-dpo-59605-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\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'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-mistral-24b-dpo-59605-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T02:59:46Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:08:16Z\', \'message\': \'Revision "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor-00001" failed with message: Container failed with:    0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.75\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m27.156s\\nuser\\t0m9.595s\\nsys\\t0m42.931s\\nstart_server.sh: line 23:   116 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:59:46Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:59:46Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T02:59:46Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T02:59:46Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'   0-31,64-95\\nNUMA node1 CPU(s):                  32-63,96-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.75\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m27.156s\\nuser\\t0m9.595s\\nsys\\t0m42.931s\\nstart_server.sh: line 23:   116 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 0.17s
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 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
%s, retrying in %s seconds...
Creating inference service chaiml-mistral-24b-dpo-59605-v4-profiler
Waiting for inference service chaiml-mistral-24b-dpo-59605-v4-profiler to be ready
Tearing down inference service chaiml-mistral-24b-dpo-59605-v4-profiler
clean up pipeline due to error=DeploymentError('Timeout to start the InferenceService chaiml-mistral-24b-dpo-59605-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\': \'2025-06-25T03:30:01Z\', \'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\': \'2025-06-25T03:30:01Z\'}, {\'apiVersion\': \'serving.kserve.io/v1beta1\', \'fieldsType\': \'FieldsV1\', \'fieldsV1\': {\'f:metadata\': {\'f:finalizers\': {\'.\': {}, \'v:"inferenceservice.finalizers"\': {}}}}, \'manager\': \'manager\', \'operation\': \'Update\', \'time\': \'2025-06-25T03:30:01Z\'}, {\'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\': \'2025-06-25T03:40:03Z\'}], \'name\': \'chaiml-mistral-24b-dpo-59605-v4-profiler\', \'namespace\': \'tenant-chaiml-guanaco\', \'resourceVersion\': \'435626747\', \'uid\': \'77804ae4-0d28-4bef-9829-f9cf3f9fb975\'}, \'spec\': {\'predictor\': {\'affinity\': {\'nodeAffinity\': {\'tion\': [{\'preference\': {\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\']}]}, \'weight\': 5}], \'requiredDuringSchedulingIgnoredDuringExecution\': {\'nodeSelectorTerms\': [{\'matchExpressions\': [{\'key\': \'gpu.nvidia.com/class\', \'operator\': \'In\', \'values\': [\'A100_NVLINK_80GB\', \'RTX_A6000\']}]}]}}}, \'containerConcurrency\': 0, \'containers\': [{\'env\': [{\'name\': \'MAX_TOKEN_INPUT\', \'value\': \'768\'}, {\'name\': \'BEST_OF\', \'value\': \'8\'}, {\'name\': \'TEMPERATURE\', \'value\': \'0.9\'}, {\'name\': \'PRESENCE_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'FREQUENCY_PENALTY\', \'value\': \'0.5\'}, {\'name\': \'TOP_P\', \'value\': \'0.9\'}, {\'name\': \'MIN_P\', \'value\': \'0.6\'}, {\'name\': \'TOP_K\', \'value\': \'80\'}, {\'name\': \'STOPPING_WORDS\', \'value\': \'["\\\\\\\\n", "</s>", "###", "You:"]\'}, {\'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-mistral-24b-dpo-59605-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\': \'26Gi\', \'nvidia.com/gpu\': \'1\'}, \'requests\': {\'cpu\': \'2\', \'memory\': \'26Gi\', \'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-mistral-24b-dpo-59605-v4-profiler-predictor-00001\'}}, \'conditions\': [{\'lastTransitionTime\': \'2025-06-25T03:31:17Z\', \'reason\': \'PredictorConfigurationReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'LatestDeploymentReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:40:03Z\', \'message\': \'Revision "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor-00001" failed with message: Container failed with: 2-47,96-111\\nNUMA node3 CPU(s):                  48-63,112-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.124\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m24.543s\\nuser\\t0m8.310s\\nsys\\t0m39.531s\\nstart_server.sh: line 23:   119 Killed                  python3 main.py\\n.\', \'reason\': \'RevisionFailed\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorConfigurationReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:31:17Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'PredictorReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:31:17Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'PredictorRouteReady\'}, {\'lastTransitionTime\': \'2025-06-25T03:31:17Z\', \'message\': \'Configuration "chaiml-mistral-24b-dpo-59605-v4-profiler-predictor" does not have any ready Revision.\', \'reason\': \'RevisionMissing\', \'status\': \'False\', \'type\': \'Ready\'}, {\'lastTransitionTime\': \'2025-06-25T03:31:17Z\', \'reason\': \'PredictorRouteReady not ready\', \'severity\': \'Info\', \'status\': \'False\', \'type\': \'RoutesReady\'}], \'modelStatus\': {\'lastFailureInfo\': {\'exitCode\': 137, \'message\': \'2-47,96-111\\nNUMA node3 CPU(s):                  48-63,112-127\\nVulnerability Gather data sampling: Mitigation; Microcode\\nVulnerability Itlb multihit:        Not affected\\nVulnerability L1tf:                 Not affected\\nVulnerability Mds:                  Not affected\\nVulnerability Meltdown:             Not affected\\nVulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable\\nVulnerability Retbleed:             Not affected\\nVulnerability Spec rstack overflow: Not affected\\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; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI Syscall hardening, KVM SW loop\\nVulnerability Srbds:                Not affected\\nVulnerability Tsx async abort:      Not affected\\nGPU: 81920 MiB, NVIDIA A100-SXM4-80GB\\nIP: 216.153.55.124\\ndownloading s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4 to /dev/shm/model_cache\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/config.json /dev/shm/model_cache/config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/special_tokens_map.json /dev/shm/model_cache/special_tokens_map.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer_config.json /dev/shm/model_cache/tokenizer_config.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/tokenizer.json /dev/shm/model_cache/tokenizer.json\\ncp s3://guanaco-mkml-models/chaiml-mistral-24b-dpo-59605-v4/flywheel_model.4.safetensors /dev/shm/model_cache/flywheel_model.4.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\\t0m24.543s\\nuser\\t0m8.310s\\nsys\\t0m39.531s\\nstart_server.sh: line 23:   119 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
chaiml-mistral-24b-dpo-_59605_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral-24b-dpo-_59605_v4 status is now torndown due to DeploymentManager action