developer_uid: rirv938
submission_id: chaiml-q235b-kimi-v3-wi_81678_v1
model_name: chaiml-q235b-kimi-v3-wi_81678_v1
model_group: ChaiML/q235b_kimi_v3_wit
status: torndown
timestamp: 2026-04-06T12:37:19+00:00
num_battles: 10388
num_wins: 5729
celo_rating: 1339.98
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged
model_architecture: Qwen3MoeForCausalLM
model_num_parameters: 1821417132032.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 80
reward_model: default
display_name: chaiml-q235b-kimi-v3-wi_81678_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged
model_size: 1821B
ranking_group: single
us_pacific_date: 2026-04-03
win_ratio: 0.5515017327685792
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|>', '</s>', '<|assistant|>', '</think>', '<|user|>', '####'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s persona: {memory}<|im_end|>\n", 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', '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 chaiml-q235b-kimi-v3-wi-81678-v1-uploader
Waiting for job on chaiml-q235b-kimi-v3-wi-81678-v1-uploader to finish
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Using quantization_mode: w4a16
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Checking if ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged-W4A16 already exists in ChaiML
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Downloading snapshot of ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged...
2026-04-03T07:09:02.381363+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:10:02.467507+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:11:02.564702+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Downloaded in 170.105s
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Applying quantization...
2026-04-03T07:12:02.665812+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:11:58 INFO __init__.py L202: Patched transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeSparseMoeBlock -> auto_round.modeling.unfused_moe.qwen3_moe.LinearQwen3MoeSparseMoeBlock
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:19 INFO base.py L448: `enable_opt_rtn` is turned on, set `--disable_opt_rtn` for higher speed at the cost of accuracy.
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:19 INFO base.py L486: using torch.bfloat16 for quantization tuning
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:19 INFO base.py L1573: Using predefined ignore_layers: ['mlp.gate']
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:21 INFO base.py L1081: start to compute imatrix
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:50 WARNING base.py L1201: MoE layer detected: optimized RTN is disabled for efficiency. Use `--enable_opt_rtn` to force-enable it for MoE layers.
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:52 INFO device.py L1468: 'peak_ram': 18.82GB, 'peak_vram': 11.38GB
2026-04-03T07:13:02.774808+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:12:59 INFO device.py L1468: 'peak_ram': 20.2GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:06 INFO device.py L1468: 'peak_ram': 21.55GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:19 INFO device.py L1468: 'peak_ram': 26.98GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:28 INFO device.py L1468: 'peak_ram': 26.98GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:36 INFO device.py L1468: 'peak_ram': 26.98GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:44 INFO device.py L1468: 'peak_ram': 26.98GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:13:56 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:14:02.862708+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:02 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:08 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:15 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:24 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:31 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:37 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:44 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:14:53 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:15:02.954520+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:00 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:06 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:12 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:22 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:29 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:35 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:41 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:51 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:15:57 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:16:03.047598+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:04 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:10 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:19 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:26 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:32 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:38 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:48 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:16:55 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:17:03.136058+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:01 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:07 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:17 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:23 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:30 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:36 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:45 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:52 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:17:58 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:18:03.233242+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:08 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:14 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:20 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:26 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:36 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:42 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:49 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:18:55 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:19:03.328700+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:04 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:11 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:17 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:23 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:33 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:39 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:46 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:19:52 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:20:03.421167+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:01 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:08 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:20 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:36 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:42 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:48 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:20:58 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:21:03.519793+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:04 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:10 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:17 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:26 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:32 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:38 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:45 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:21:54 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:00 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:22:03.641028+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:07 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:13 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:22 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:29 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:35 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:44 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:50 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:23:03.734913+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:22:57 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:03 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:12 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:19 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:25 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:31 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:41 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:47 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:53 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
2026-04-03T07:24:03.843038+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:23:59 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:24:08 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:24:11 INFO shard_writer.py L208: model has been saved to /dev/shm/model_output/
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:24:12 WARNING export.py L336: /dev/shm/model_output already exists, this may cause model conflict
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: 2026-04-03 07:24:12 INFO device.py L1468: 'peak_ram': 27.66GB, 'peak_vram': 11.38GB
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Checking if ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged-W4A16 already exists in ChaiML
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Creating repo ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged-W4A16 and uploading /dev/shm/model_output to it
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: ---------- 2026-04-03 07:24:12 (0:00:00) ----------
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Files: hashed 7/32 (21.5M/131.9G) | pre-uploaded: 0/1 (0.0/131.9G) (+31 unsure) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Workers: hashing: 25 | get upload mode: 4 | pre-uploading: 0 | committing: 0 | waiting: 35
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: ---------------------------------------------------
2026-04-03T07:25:03.973504+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader:       
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: ---------- 2026-04-03 07:25:13 (0:01:00) ----------
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Files: hashed 32/32 (131.9G/131.9G) | pre-uploaded: 9/26 (40.6G/131.9G) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Workers: hashing: 0 | get upload mode: 0 | pre-uploading: 17 | committing: 0 | waiting: 47
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: ---------------------------------------------------
2026-04-03T07:26:04.094428+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Processed model ChaiML/q235b_kimi_v3_with_reward_fix-step432-merged in 1056.792s
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/tokenizer_config.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/quantization_config.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/generation_config.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/config.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/chat_template.jinja
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model.safetensors.index.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/tokenizer.json
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00025-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00025-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00002-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00002-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00013-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00013-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00024-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00024-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00008-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00008-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00010-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00010-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00016-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00016-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00017-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00017-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00003-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00003-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00004-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00004-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00018-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00018-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00020-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00020-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00009-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00009-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00011-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00011-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00014-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00014-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00005-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00005-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00021-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00021-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00015-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00015-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00023-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00023-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00019-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00019-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00012-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00012-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00007-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00007-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00006-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00006-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00001-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00001-of-00025.safetensors
chaiml-q235b-kimi-v3-wi-81678-v1-uploader: cp /dev/shm/model_output/model-00022-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-kimi-v3-wi-81678-v1/default/model-00022-of-00025.safetensors
Job chaiml-q235b-kimi-v3-wi-81678-v1-uploader completed after 1139.13s with status: succeeded
Stopping job with name chaiml-q235b-kimi-v3-wi-81678-v1-uploader
Pipeline stage VLLMUploader completed in 1139.66s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.14s
run pipeline stage %s
Running pipeline stage VLLMTemplater
2026-04-03T07:27:04.204277+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
Pipeline stage VLLMTemplater completed in 1.86s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-kimi-v3-wi-81678-v1
Waiting for inference service chaiml-q235b-kimi-v3-wi-81678-v1 to be ready
2026-04-03T07:28:04.310293+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:29:04.462169+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:30:04.625591+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:31:04.747169+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:32:04.866342+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:33:05.030522+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
2026-04-03T07:34:05.172770+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
Inference service chaiml-q235b-kimi-v3-wi-81678-v1 ready after 431.355491399765s
Pipeline stage VLLMDeployer completed in 431.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4579126834869385s
Received healthy response to inference request in 1.5707831382751465s
Received healthy response to inference request in 1.561009168624878s
Received healthy response to inference request in 1.4827017784118652s
Received healthy response to inference request in 2.1798758506774902s
Received healthy response to inference request in 1.4497318267822266s
Received healthy response to inference request in 1.5166008472442627s
Received healthy response to inference request in 1.569530725479126s
Received healthy response to inference request in 1.4383907318115234s
Received healthy response to inference request in 1.4679102897644043s
Received healthy response to inference request in 1.4341073036193848s
Received healthy response to inference request in 1.4792001247406006s
Received healthy response to inference request in 1.4532341957092285s
Received healthy response to inference request in 1.6589126586914062s
Received healthy response to inference request in 1.512871503829956s
Received healthy response to inference request in 1.729825735092163s
Received healthy response to inference request in 1.608546495437622s
Received healthy response to inference request in 1.5617187023162842s
Received healthy response to inference request in 1.4600448608398438s
Received healthy response to inference request in 1.5396006107330322s
Received healthy response to inference request in 1.4763526916503906s
Received healthy response to inference request in 1.4573993682861328s
Received healthy response to inference request in 1.5909700393676758s
Received healthy response to inference request in 1.4645633697509766s
Received healthy response to inference request in 1.5516211986541748s
Received healthy response to inference request in 1.5770595073699951s
Received healthy response to inference request in 1.6882672309875488s
Received healthy response to inference request in 1.5908739566802979s
2026-04-03T07:35:05.291654+00:00 monitor updated for chaiml-q235b-kimi-v3-wi_81678_v1
Received healthy response to inference request in 2.22816801071167s
Received healthy response to inference request in 2.048646926879883s
30 requests
0 failed requests
5th percentile: 1.4434942245483398
10th percentile: 1.4528839588165283
20th percentile: 1.46365966796875
30th percentile: 1.4783458948135375
40th percentile: 1.51510910987854
50th percentile: 1.5563151836395264
60th percentile: 1.5700316905975342
70th percentile: 1.5909027814865113
80th percentile: 1.6647835731506349
90th percentile: 2.0617698192596436
95th percentile: 2.206436538696289
99th percentile: 3.1012867283821115
mean time: 1.6602143843968709
Pipeline stage StressChecker completed in 53.50s
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 1.61s
Shutdown handler de-registered
chaiml-q235b-kimi-v3-wi_81678_v1 status is now deployed due to DeploymentManager action
chaiml-q235b-kimi-v3-wi_81678_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-q235b-kimi-v3-wi_81678_v1 status is now torndown due to DeploymentManager action