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-qwen3-4bskywork-78097-v2-mkmlizer
Waiting for job on chaiml-qwen3-4bskywork-78097-v2-mkmlizer to finish
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Version: 0.29.15 ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ belonging to: ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ║ ║
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: Downloaded to shared memory in 24.863s
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: Checking if ChaiML/qwen3-4bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step200k-555acc already exists in ChaiML
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp1nx5b3c5, device:0
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: quantized model in 24.590s
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: Processed model ChaiML/qwen3-4bskywork-v2-try1-new8m-filterv3-4m-full-512seq-step200k-555acc in 49.454s
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/config.json
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/added_tokens.json
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/special_tokens_map.json
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/tokenizer_config.json
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/merges.txt
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/vocab.json
chaiml-qwen3-4bskywork-78097-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen3-4bskywork-78097-v2/nvidia/tokenizer.json
Job chaiml-qwen3-4bskywork-78097-v2-mkmlizer completed after 75.35s with status: succeeded
Stopping job with name chaiml-qwen3-4bskywork-78097-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.11s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen3-4bskywork-78097-v2
Waiting for inference service chaiml-qwen3-4bskywork-78097-v2 to be ready
Failed to get response for submission chaiml-mistralnemo-nis-_16053_v3: HTTPConnectionPool(host='chaiml-mistralnemo-nis-16053-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-qwen3-4bskywork-78097-v2 ready after 201.96732759475708s
Pipeline stage MKMLDeployer completed in 202.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.018155097961426s
Received healthy response to inference request in 4.606257200241089s
Received healthy response to inference request in 3.4670615196228027s
Received healthy response to inference request in 3.4521560668945312s
Received healthy response to inference request in 4.431633472442627s
5 requests
0 failed requests
5th percentile: 3.4551371574401855
10th percentile: 3.4581182479858397
20th percentile: 3.4640804290771485
30th percentile: 3.5772802352905275
40th percentile: 3.7977176666259767
50th percentile: 4.018155097961426
60th percentile: 4.183546447753907
70th percentile: 4.3489377975463865
80th percentile: 4.466558218002319
90th percentile: 4.536407709121704
95th percentile: 4.5713324546813965
99th percentile: 4.59927225112915
mean time: 3.995052671432495
Pipeline stage StressChecker completed in 22.00s
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 0.79s
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 0.93s
Shutdown handler de-registered
chaiml-qwen3-4bskywork-_78097_v2 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 0.11s
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-qwen3-4bskywork-78097-v2-profiler
Waiting for inference service chaiml-qwen3-4bskywork-78097-v2-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 7393.51s
Shutdown handler de-registered
chaiml-qwen3-4bskywork-_78097_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen3-4bskywork-_78097_v2 status is now torndown due to DeploymentManager action