qwen-qwen3-5-35b-a3b

developer_uid: richhx
submission_id: qwen-qwen3-5-35b-a3b_v50
model_name: qwen-qwen3-5-35b-a3b_v50
model_group: Qwen/Qwen3.5-35B-A3B
status: torndown
timestamp: 2026-03-28T00:57:05+00:00
num_battles: 2639
num_wins: 287
celo_rating: 8476.44
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: Qwen/Qwen3.5-35B-A3B
model_architecture: Qwen3_5MoeForConditionalGeneration
model_num_parameters: 33753909248.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: qwen-qwen3-5-35b-a3b_v50
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: Qwen/Qwen3.5-35B-A3B
model_size: 34B
ranking_group: single
us_pacific_date: 2026-03-24
win_ratio: 0.10875331564986737
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|>', '####\n', '\n', '####', '<|endoftext|>', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:<think></think>', '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 VLLMUploader
Starting job with name qwen-qwen3-5-35b-a3b-v50-uploader
Waiting for job on qwen-qwen3-5-35b-a3b-v50-uploader to finish
qwen-qwen3-5-35b-a3b-v50-uploader: Using quantization_mode: none
qwen-qwen3-5-35b-a3b-v50-uploader: Downloading snapshot of Qwen/Qwen3.5-35B-A3B...
qwen-qwen3-5-35b-a3b-v50-uploader: Downloaded in 23.361s
qwen-qwen3-5-35b-a3b-v50-uploader: Processed model Qwen/Qwen3.5-35B-A3B in 50.271s
qwen-qwen3-5-35b-a3b-v50-uploader: creating bucket guanaco-vllm-models
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v50-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
qwen-qwen3-5-35b-a3b-v50-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
2026-03-25T00:26:07.452889+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
qwen-qwen3-5-35b-a3b-v50-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v50-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v50-uploader:   if re.search("-\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v50-uploader:   if re.search("\.\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
qwen-qwen3-5-35b-a3b-v50-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
qwen-qwen3-5-35b-a3b-v50-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
qwen-qwen3-5-35b-a3b-v50-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
qwen-qwen3-5-35b-a3b-v50-uploader: Bucket 's3://guanaco-vllm-models/' created
qwen-qwen3-5-35b-a3b-v50-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/.gitattributes
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/LICENSE s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/LICENSE
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/tokenizer_config.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/config.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/tokenizer.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/video_preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/video_preprocessor_config.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors.index.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/generation_config.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/preprocessor_config.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/README.md
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/chat_template.jinja
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/vocab.json
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/merges.txt
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00014-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00014-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00002-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00002-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00003-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00003-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00010-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00010-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00011-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00011-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00013-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00013-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00008-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00008-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00005-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00005-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00004-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00004-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00006-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00006-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00012-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00012-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v50-uploader: cp /dev/shm/model_output/model.safetensors-00001-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v50/default/model.safetensors-00001-of-00014.safetensors
Job qwen-qwen3-5-35b-a3b-v50-uploader completed after 83.56s with status: succeeded
Stopping job with name qwen-qwen3-5-35b-a3b-v50-uploader
Pipeline stage VLLMUploader completed in 84.19s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 3.22s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service qwen-qwen3-5-35b-a3b-v50
Waiting for inference service qwen-qwen3-5-35b-a3b-v50 to be ready
2026-03-25T00:27:07.754718+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
2026-03-25T00:28:07.877076+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
Connection pool is full, discarding connection: %s. Connection pool size: %s
2026-03-25T00:29:07.971742+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
2026-03-25T00:30:08.063722+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
Inference service qwen-qwen3-5-35b-a3b-v50 ready after 221.40663194656372s
Pipeline stage VLLMDeployer completed in 221.97s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-25T00:31:08.564565+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-25T00:32:08.720690+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.799483060836792s
Received healthy response to inference request in 3.099954843521118s
Received healthy response to inference request in 1.0603513717651367s
Received healthy response to inference request in 0.469865083694458s
Received healthy response to inference request in 2.7202486991882324s
Received healthy response to inference request in 3.511608600616455s
Received healthy response to inference request in 0.27718234062194824s
Received healthy response to inference request in 1.3707756996154785s
Received healthy response to inference request in 0.9069275856018066s
Received healthy response to inference request in 1.1787893772125244s
Received healthy response to inference request in 4.094601392745972s
Received healthy response to inference request in 0.43500709533691406s
Received healthy response to inference request in 0.5770289897918701s
Received healthy response to inference request in 0.8610489368438721s
Received healthy response to inference request in 0.9304549694061279s
Received healthy response to inference request in 0.8726902008056641s
Received healthy response to inference request in 0.5276360511779785s
Received healthy response to inference request in 0.30284953117370605s
Received healthy response to inference request in 0.3072168827056885s
Received healthy response to inference request in 1.5854876041412354s
2026-03-25T00:33:08.849033+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v50
Received healthy response to inference request in 0.8664798736572266s
Received healthy response to inference request in 0.5901732444763184s
Received healthy response to inference request in 0.4733254909515381s
30 requests
7 failed requests
5th percentile: 0.30481483936309817
10th percentile: 0.42222807407379154
20th percentile: 0.5167739391326904
30th percentile: 0.7797862291336057
40th percentile: 0.8932326316833497
50th percentile: 1.1195703744888306
60th percentile: 2.0393920421600327
70th percentile: 3.223450970649718
80th percentile: 20.14686460494995
90th percentile: 20.21826684474945
95th percentile: 20.272389829158783
99th percentile: 20.442340264320375
mean time: 5.719236365954081
%s, retrying in %s seconds...
Received healthy response to inference request in 0.35730504989624023s
Received healthy response to inference request in 0.7494251728057861s
Received healthy response to inference request in 0.2873344421386719s
Received healthy response to inference request in 0.28777003288269043s
Received healthy response to inference request in 0.6780667304992676s
Received healthy response to inference request in 0.3288230895996094s
Received healthy response to inference request in 0.28112149238586426s
Received healthy response to inference request in 0.36895060539245605s
Received healthy response to inference request in 0.9487524032592773s
Received healthy response to inference request in 0.2726619243621826s
Received healthy response to inference request in 0.5074610710144043s
Received healthy response to inference request in 0.2525160312652588s
Received healthy response to inference request in 0.7263510227203369s
Received healthy response to inference request in 0.245253324508667s
Received healthy response to inference request in 0.8136992454528809s
Received healthy response to inference request in 0.2688140869140625s
Received healthy response to inference request in 0.3416478633880615s
Received healthy response to inference request in 0.34571051597595215s
Received healthy response to inference request in 0.32950782775878906s
Received healthy response to inference request in 0.4155097007751465s
Received healthy response to inference request in 0.4324789047241211s
Received healthy response to inference request in 0.9797995090484619s
Received healthy response to inference request in 0.9440195560455322s
Received healthy response to inference request in 0.22501397132873535s
Received healthy response to inference request in 0.7883684635162354s
Received healthy response to inference request in 0.38860654830932617s
Received healthy response to inference request in 0.3985023498535156s
Received healthy response to inference request in 0.5178110599517822s
Received healthy response to inference request in 0.5002357959747314s
Received healthy response to inference request in 0.47644782066345215s
30 requests
0 failed requests
5th percentile: 0.2485215425491333
10th percentile: 0.26718428134918215
20th percentile: 0.28609185218811034
30th percentile: 0.32930240631103513
40th percentile: 0.352667236328125
50th percentile: 0.3935544490814209
60th percentile: 0.4500664710998534
70th percentile: 0.5105660676956176
80th percentile: 0.7309658527374269
90th percentile: 0.8267312765121462
95th percentile: 0.946622622013092
99th percentile: 0.9707958483695984
mean time: 0.4819321870803833
Pipeline stage StressChecker completed in 192.97s
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 1.50s
Shutdown handler de-registered
qwen-qwen3-5-35b-a3b_v50 status is now deployed due to DeploymentManager action
qwen-qwen3-5-35b-a3b_v50 status is now inactive due to system request
qwen-qwen3-5-35b-a3b_v50 status is now torndown due to DeploymentManager action