qwen-qwen3-5-35b-a3b

developer_uid: richhx
submission_id: qwen-qwen3-5-35b-a3b_v51
model_name: qwen-qwen3-5-35b-a3b_v51
model_group: Qwen/Qwen3.5-35B-A3B
status: inactive
timestamp: 2026-03-25T01:48:41+00:00
num_battles: 13307
num_wins: 6155
celo_rating: 8476.27
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_v51
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: 0.4625385135642895
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': ['####\n', '####', '<|im_end|>', '<|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-v51-uploader
Waiting for job on qwen-qwen3-5-35b-a3b-v51-uploader to finish
qwen-qwen3-5-35b-a3b-v51-uploader: Using quantization_mode: none
qwen-qwen3-5-35b-a3b-v51-uploader: Downloading snapshot of Qwen/Qwen3.5-35B-A3B...
2026-03-25T00:45:05.286961+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
qwen-qwen3-5-35b-a3b-v51-uploader: Processed model Qwen/Qwen3.5-35B-A3B in 50.010s
qwen-qwen3-5-35b-a3b-v51-uploader: creating bucket guanaco-vllm-models
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v51-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
qwen-qwen3-5-35b-a3b-v51-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v51-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v51-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v51-uploader:   if re.search("-\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v51-uploader:   if re.search("\.\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
qwen-qwen3-5-35b-a3b-v51-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
qwen-qwen3-5-35b-a3b-v51-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
qwen-qwen3-5-35b-a3b-v51-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
qwen-qwen3-5-35b-a3b-v51-uploader: Bucket 's3://guanaco-vllm-models/' created
qwen-qwen3-5-35b-a3b-v51-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/chat_template.jinja
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/generation_config.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/config.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/.gitattributes
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/README.md
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/model.safetensors.index.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/LICENSE s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/LICENSE
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/video_preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/video_preprocessor_config.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/preprocessor_config.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/tokenizer_config.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/merges.txt
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/vocab.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/tokenizer.json
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/model.safetensors-00014-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/model.safetensors-00014-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/model.safetensors-00010-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/model.safetensors-00010-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/model.safetensors-00006-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/model.safetensors-00006-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v51-uploader: cp /dev/shm/model_output/model.safetensors-00009-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v51/default/model.safetensors-00009-of-00014.safetensors
Job qwen-qwen3-5-35b-a3b-v51-uploader completed after 91.09s with status: succeeded
Stopping job with name qwen-qwen3-5-35b-a3b-v51-uploader
Pipeline stage VLLMUploader completed in 91.71s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 3.07s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service qwen-qwen3-5-35b-a3b-v51
Waiting for inference service qwen-qwen3-5-35b-a3b-v51 to be ready
2026-03-25T00:46:05.377155+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
2026-03-25T00:47:05.474694+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
2026-03-25T00:48:05.562848+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
2026-03-25T00:49:05.650493+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
Inference service qwen-qwen3-5-35b-a3b-v51 ready after 210.60014152526855s
Pipeline stage VLLMDeployer completed in 211.10s
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!
2026-03-25T00:50:05.748585+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
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 10.925457239151001s
Received healthy response to inference request in 2.0526556968688965s
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 4.760544061660767s
Received healthy response to inference request in 12.784128665924072s
Received healthy response to inference request in 2.448719024658203s
2026-03-25T00:51:05.837365+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
Received healthy response to inference request in 1.3226673603057861s
Received healthy response to inference request in 1.7248363494873047s
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 3.5854032039642334s
Received healthy response to inference request in 2.321932554244995s
Received healthy response to inference request in 1.324218511581421s
Received healthy response to inference request in 2.0599277019500732s
Received healthy response to inference request in 1.442807912826538s
2026-03-25T00:52:05.927338+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
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 1.383582353591919s
Received healthy response to inference request in 2.6936445236206055s
Received healthy response to inference request in 1.4045846462249756s
Received healthy response to inference request in 2.1545722484588623s
Received healthy response to inference request in 2.1166539192199707s
Received healthy response to inference request in 1.4243028163909912s
Received healthy response to inference request in 1.3672711849212646s
Received healthy response to inference request in 1.4263007640838623s
Received healthy response to inference request in 1.8381836414337158s
Received healthy response to inference request in 1.9336597919464111s
Received healthy response to inference request in 1.9537723064422607s
30 requests
7 failed requests
5th percentile: 1.3435922145843506
10th percentile: 1.3819512367248534
20th percentile: 1.425901174545288
30th percentile: 1.8041794538497924
40th percentile: 2.0131023406982425
50th percentile: 2.1356130838394165
60th percentile: 2.546689224243164
70th percentile: 6.610018014907819
80th percentile: 20.110235595703124
90th percentile: 20.119539880752562
95th percentile: 20.13300017118454
99th percentile: 20.19418321609497
mean time: 6.912951334317525
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3129267692565918s
Received healthy response to inference request in 1.8940792083740234s
Received healthy response to inference request in 1.4345109462738037s
Received healthy response to inference request in 1.4242606163024902s
Received healthy response to inference request in 1.323836326599121s
Received healthy response to inference request in 1.4759469032287598s
Received healthy response to inference request in 2.207662343978882s
Received healthy response to inference request in 1.6588153839111328s
Received healthy response to inference request in 1.421513557434082s
Received healthy response to inference request in 1.336684226989746s
Received healthy response to inference request in 1.4169938564300537s
Received healthy response to inference request in 1.4005186557769775s
Received healthy response to inference request in 1.3382761478424072s
Received healthy response to inference request in 1.3504974842071533s
Received healthy response to inference request in 1.4687187671661377s
2026-03-25T00:53:06.017265+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v51
Received healthy response to inference request in 1.3485455513000488s
Received healthy response to inference request in 1.775707483291626s
Received healthy response to inference request in 1.4421310424804688s
Received healthy response to inference request in 1.7299702167510986s
Received healthy response to inference request in 1.8755500316619873s
Received healthy response to inference request in 1.5330212116241455s
Received healthy response to inference request in 1.4938218593597412s
Received healthy response to inference request in 1.9436113834381104s
Received healthy response to inference request in 1.3918039798736572s
Received healthy response to inference request in 1.4424331188201904s
Received healthy response to inference request in 1.4156887531280518s
Received healthy response to inference request in 1.6125290393829346s
Received healthy response to inference request in 1.3354134559631348s
Received healthy response to inference request in 1.3925039768218994s
Received healthy response to inference request in 1.4874918460845947s
30 requests
0 failed requests
5th percentile: 1.3290460348129272
10th percentile: 1.336557149887085
20th percentile: 1.3501070976257323
30th percentile: 1.3981142520904541
40th percentile: 1.4197056770324707
50th percentile: 1.4383209943771362
60th percentile: 1.4716100215911865
70th percentile: 1.5055816650390623
80th percentile: 1.6730463504791262
90th percentile: 1.877402949333191
95th percentile: 1.921321904659271
99th percentile: 2.1310875654220585
mean time: 1.5228488047917683
Pipeline stage StressChecker completed in 258.59s
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 1.44s
Shutdown handler de-registered
qwen-qwen3-5-35b-a3b_v51 status is now deployed due to DeploymentManager action
qwen-qwen3-5-35b-a3b_v51 status is now inactive due to auto deactivation removed underperforming models