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-opus-v2-ju-81750-v1-uploader
Waiting for job on chaiml-q235b-opus-v2-ju-81750-v1-uploader to finish
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Using quantization_mode: w4a16
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Checking if ChaiML/q235b_opus_v2_judging-step414-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Downloading snapshot of ChaiML/q235b_opus_v2_judging-step414-merged...
2026-04-02T06:36:56.645223+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T06:37:56.733988+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T06:38:56.824039+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Downloaded in 165.835s
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Applying quantization...
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:39:31 INFO __init__.py L202: Patched transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeSparseMoeBlock -> auto_round.modeling.unfused_moe.qwen3_moe.LinearQwen3MoeSparseMoeBlock[0m
2026-04-02T06:39:56.919359+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:39:59 INFO base.py L448: `enable_opt_rtn` is turned on, set `--disable_opt_rtn` for higher speed at the cost of accuracy.[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:39:59 INFO base.py L486: using torch.bfloat16 for quantization tuning[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:40:00 INFO base.py L1573: Using predefined ignore_layers: ['mlp.gate'][0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:40:02 INFO base.py L1081: start to compute imatrix[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [33;1m2026-04-02 06:40:31 WARNING base.py L1201: MoE layer detected: optimized RTN is disabled for efficiency. Use `--enable_opt_rtn` to force-enable it for MoE layers.[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:40:33 INFO device.py L1468: 'peak_ram': 19.06GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:40:41 INFO device.py L1468: 'peak_ram': 20.43GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:40:49 INFO device.py L1468: 'peak_ram': 21.75GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:40:57.016785+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:02 INFO device.py L1468: 'peak_ram': 27.18GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:10 INFO device.py L1468: 'peak_ram': 27.18GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:21 INFO device.py L1468: 'peak_ram': 27.18GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:32 INFO device.py L1468: 'peak_ram': 27.18GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:46 INFO device.py L1468: 'peak_ram': 27.82GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:41:57.113307+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:52 INFO device.py L1468: 'peak_ram': 27.82GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:41:59 INFO device.py L1468: 'peak_ram': 27.82GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:05 INFO device.py L1468: 'peak_ram': 27.82GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:15 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:22 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:28 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:35 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:45 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:51 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:42:57.243237+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:42:57 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:04 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:13 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:20 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:26 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:43 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:49 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:43:57.333097+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:43:55 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:02 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:11 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:18 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:24 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:31 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:40 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:47 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:44:53 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:44:57.431540+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:00 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:09 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:16 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:22 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:29 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:38 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:45 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:45:51 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:45:57.531516+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:01 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:07 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:13 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:20 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:29 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:42 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:48 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:46:57.627112+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:46:58 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:04 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:11 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:17 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:27 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:33 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:39 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:46 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:47:55 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:47:57.724040+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:02 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:08 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:14 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:23 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:30 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:36 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:43 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:48:57.870232+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:52 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:48:58 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:05 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:11 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:21 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:27 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:33 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:39 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:49:57.959998+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:49 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:49:55 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:02 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:08 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:17 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:24 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:40 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:46 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:52 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:50:58.052926+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:50:59 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:08 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:14 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:21 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:27 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:43 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:49 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:51:55 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
2026-04-02T06:51:58.151023+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:52:05 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:52:08 INFO shard_writer.py L208: model has been saved to /dev/shm/model_output/[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [33;1m2026-04-02 06:52:09 WARNING export.py L336: /dev/shm/model_output already exists, this may cause model conflict[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: [38;20m2026-04-02 06:52:09 INFO device.py L1468: 'peak_ram': 27.85GB, 'peak_vram': 11.38GB[0m
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Checking if ChaiML/q235b_opus_v2_judging-step414-merged-W4A16 already exists in ChaiML
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Creating repo ChaiML/q235b_opus_v2_judging-step414-merged-W4A16 and uploading /dev/shm/model_output to it
chaiml-q235b-opus-v2-ju-81750-v1-uploader: ---------- 2026-04-02 06:52:10 (0:00:00) ----------
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Files: hashed 7/32 (21.5M/131.9G) | pre-uploaded: 0/0 (0.0/131.9G) (+31 unsure) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Workers: hashing: 25 | get upload mode: 1 | pre-uploading: 0 | committing: 0 | waiting: 38
chaiml-q235b-opus-v2-ju-81750-v1-uploader: ---------------------------------------------------
2026-04-02T06:52:58.251363+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader:
[K[F
[K[F
[K[F
[K[F
[K[F
[K[F
[K[F
chaiml-q235b-opus-v2-ju-81750-v1-uploader: ---------- 2026-04-02 06:53:10 (0:01:00) ----------
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Files: hashed 32/32 (131.9G/131.9G) | pre-uploaded: 10/26 (46.0G/131.9G) | committed: 0/32 (0.0/131.9G) | ignored: 0
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Workers: hashing: 0 | get upload mode: 0 | pre-uploading: 16 | committing: 0 | waiting: 48
chaiml-q235b-opus-v2-ju-81750-v1-uploader: ---------------------------------------------------
2026-04-02T06:53:58.346673+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Processed model ChaiML/q235b_opus_v2_judging-step414-merged in 1058.526s
chaiml-q235b-opus-v2-ju-81750-v1-uploader: creating bucket guanaco-vllm-models
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: if re.search("-\.", bucket, re.UNICODE):
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: if re.search("\.\.", bucket, re.UNICODE):
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-q235b-opus-v2-ju-81750-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-q235b-opus-v2-ju-81750-v1-uploader: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-q235b-opus-v2-ju-81750-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-q235b-opus-v2-ju-81750-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/chat_template.jinja
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/generation_config.json
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/quantization_config.json
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/tokenizer_config.json
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/config.json
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model.safetensors.index.json
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/tokenizer.json
2026-04-02T06:54:58.444998+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: DEBUG retryable error: InternalError: We encountered an internal error, please try again.
chaiml-q235b-opus-v2-ju-81750-v1-uploader: status code: 500, request id: 498d5176-bc86-9fe3-b47b-38ebf55c88e0, host id:
chaiml-q235b-opus-v2-ju-81750-v1-uploader: DEBUG retryable error: InternalError: We encountered an internal error, please try again.
chaiml-q235b-opus-v2-ju-81750-v1-uploader: status code: 500, request id: 28f08f86-a491-9c03-884a-d879521e19a1, host id:
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00025-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00025-of-00025.safetensors
2026-04-02T06:55:58.543018+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00019-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00019-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00002-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00002-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00011-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00011-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00015-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00015-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00009-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00009-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00016-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00016-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00001-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00001-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00003-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00003-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00022-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00022-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00017-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00017-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00021-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00021-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00005-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00005-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00020-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00020-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00024-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00024-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00006-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00006-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00010-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00010-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00004-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00004-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00008-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00008-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00023-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00023-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00018-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00018-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00014-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00014-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00013-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00013-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00012-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00012-of-00025.safetensors
chaiml-q235b-opus-v2-ju-81750-v1-uploader: cp /dev/shm/model_output/model-00007-of-00025.safetensors s3://guanaco-vllm-models/chaiml-q235b-opus-v2-ju-81750-v1/default/model-00007-of-00025.safetensors
Job chaiml-q235b-opus-v2-ju-81750-v1-uploader completed after 1258.46s with status: succeeded
Stopping job with name chaiml-q235b-opus-v2-ju-81750-v1-uploader
Pipeline stage VLLMUploader completed in 1258.94s
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
2026-04-02T06:56:58.662254+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
Pipeline stage VLLMTemplater completed in 3.01s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-q235b-opus-v2-ju-81750-v1
Waiting for inference service chaiml-q235b-opus-v2-ju-81750-v1 to be ready
2026-04-02T06:57:58.765661+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T06:58:58.867846+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T06:59:58.973248+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:00:59.104258+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:01:59.221577+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:02:59.331614+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:03:59.434236+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:04:59.547683+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
Retrying (%r) after connection broken by '%r': %s
2026-04-02T07:05:59.647273+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:06:59.746614+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:07:59.851534+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:08:59.953401+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:10:00.055628+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
2026-04-02T07:11:00.157831+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
Inference service chaiml-q235b-opus-v2-ju-81750-v1 ready after 852.4741773605347s
Pipeline stage VLLMDeployer completed in 853.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6580636501312256s
Received healthy response to inference request in 1.4481101036071777s
Received healthy response to inference request in 1.4586446285247803s
Received healthy response to inference request in 1.6234230995178223s
Received healthy response to inference request in 1.6390190124511719s
Received healthy response to inference request in 1.9210643768310547s
Received healthy response to inference request in 1.520941972732544s
Received healthy response to inference request in 1.8473973274230957s
Received healthy response to inference request in 1.423652172088623s
Received healthy response to inference request in 1.6360366344451904s
Received healthy response to inference request in 1.516533613204956s
Received healthy response to inference request in 2.010542392730713s
Received healthy response to inference request in 1.5184354782104492s
Received healthy response to inference request in 1.4862463474273682s
Received healthy response to inference request in 1.4495816230773926s
Received healthy response to inference request in 1.568972110748291s
Received healthy response to inference request in 1.6492526531219482s
Received healthy response to inference request in 1.4446470737457275s
Received healthy response to inference request in 1.5803909301757812s
Received healthy response to inference request in 1.4524104595184326s
Received healthy response to inference request in 1.5008890628814697s
Received healthy response to inference request in 1.4697978496551514s
Received healthy response to inference request in 1.4548683166503906s
Received healthy response to inference request in 1.6451029777526855s
Received healthy response to inference request in 1.6056365966796875s
Received healthy response to inference request in 1.6020033359527588s
Received healthy response to inference request in 1.4649059772491455s
2026-04-02T07:12:00.263710+00:00 monitor updated for chaiml-q235b-opus-v2-ju_81750_v1
Received healthy response to inference request in 1.5120809078216553s
Received healthy response to inference request in 1.448967456817627s
Received healthy response to inference request in 1.5673332214355469s
30 requests
0 failed requests
5th percentile: 1.4462054371833801
10th percentile: 1.4488817214965821
20th percentile: 1.454376745223999
30th percentile: 1.4683302879333495
40th percentile: 1.507604169845581
50th percentile: 1.5196887254714966
60th percentile: 1.573539638519287
70th percentile: 1.6109725475311278
80th percentile: 1.6402358055114745
90th percentile: 1.8547640323638916
95th percentile: 1.9702772855758663
99th percentile: 3.1802824854850784
mean time: 1.637498378753662
Pipeline stage StressChecker completed in 52.87s
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 1.73s
Shutdown handler de-registered
chaiml-q235b-opus-v2-ju_81750_v1 status is now deployed due to DeploymentManager action
chaiml-q235b-opus-v2-ju_81750_v1 status is now inactive due to auto deactivation removed underperforming models