intel-qwen3-235b-a22b-i_29740

developer_uid: chai_backend_admin

submission_id: intel-qwen3-235b-a22b-i_29740_v9

model_name: intel-qwen3-235b-a22b-i_29740_v9

model_group: Intel/Qwen3-235B-A22B-In

status: torndown

timestamp: 2025-12-21T18:31:34+00:00

num_battles: 6899

num_wins: 3600

celo_rating: 1308.15

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: Intel/Qwen3-235B-A22B-Instruct-2507-int4-mixed-AutoRound

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 8

max_input_tokens: 1992

max_output_tokens: 80

reward_model: default

display_name: intel-qwen3-235b-a22b-i_29740_v9

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: Intel/Qwen3-235B-A22B-Instruct-2507-int4-mixed-AutoRound

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-21

win_ratio: 0.5218147557617046

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '<|user|>', '</s>', '####', '<|assistant|>', '</think>'], 'max_input_tokens': 1992, 'best_of': 8, 'max_output_tokens': 80}

formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name} engaged in a roleplay with user.<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}

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 VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service intel-qwen3-235b-a22b-i-29740-v9
Waiting for inference service intel-qwen3-235b-a22b-i-29740-v9 to be ready
Inference service intel-qwen3-235b-a22b-i-29740-v9 ready after 446.63115429878235s
Pipeline stage VLLMDeployer completed in 447.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.162135362625122s
Received healthy response to inference request in 2.3820650577545166s
Received healthy response to inference request in 2.1376349925994873s
Received healthy response to inference request in 2.1277847290039062s
Received healthy response to inference request in 2.020531177520752s
Received healthy response to inference request in 2.367894411087036s
Received healthy response to inference request in 2.2985174655914307s
Received healthy response to inference request in 2.3132331371307373s
Received healthy response to inference request in 2.626347541809082s
Received healthy response to inference request in 2.4743492603302s
Received healthy response to inference request in 2.315920352935791s
Received healthy response to inference request in 2.2582905292510986s
Received healthy response to inference request in 2.2607808113098145s
Received healthy response to inference request in 2.586488962173462s
Received healthy response to inference request in 1.9586224555969238s
Received healthy response to inference request in 2.5719499588012695s
Received healthy response to inference request in 1.918079137802124s
Received healthy response to inference request in 2.510526418685913s
Received healthy response to inference request in 2.173290729522705s
Received healthy response to inference request in 1.9488673210144043s
Received healthy response to inference request in 2.1938278675079346s
Received healthy response to inference request in 2.1111953258514404s
Received healthy response to inference request in 1.994800090789795s
Received healthy response to inference request in 1.9116175174713135s
Received healthy response to inference request in 2.258458137512207s
Received healthy response to inference request in 1.9745237827301025s
Received healthy response to inference request in 2.5512614250183105s
Received healthy response to inference request in 2.32006573677063s
Received healthy response to inference request in 2.32010817527771s
Received healthy response to inference request in 2.415644884109497s
30 requests
0 failed requests
5th percentile: 1.9319338202476501
10th percentile: 1.957646942138672
20th percentile: 2.0153849601745604
30th percentile: 2.134679913520813
40th percentile: 2.185613012313843
50th percentile: 2.2596194744110107
60th percentile: 2.314308023452759
70th percentile: 2.334444046020508
80th percentile: 2.427385759353638
90th percentile: 2.5533302783966065
95th percentile: 2.5799464106559755
99th percentile: 2.614788553714752
mean time: 2.248827091852824
Pipeline stage StressChecker completed in 71.55s
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 1.03s
Shutdown handler de-registered
intel-qwen3-235b-a22b-i_29740_v9 status is now deployed due to DeploymentManager action
intel-qwen3-235b-a22b-i_29740_v9 status is now inactive due to auto deactivation removed underperforming models
intel-qwen3-235b-a22b-i_29740_v9 status is now torndown due to DeploymentManager action