developer_uid: richhx
submission_id: zai-org-glm-5-fp8_v15
model_name: zai-org-glm-5-fp8_v15
model_group: zai-org/GLM-5-FP8
status: torndown
timestamp: 2026-03-27T05:56:35+00:00
num_battles: 11290
num_wins: 6420
celo_rating: 1345.73
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: zai-org/GLM-5-FP8
model_architecture: GlmMoeDsaForCausalLM
model_num_parameters: 31348144128.0
best_of: 8
max_input_tokens: 1500
max_output_tokens: 80
reward_model: default
display_name: zai-org-glm-5-fp8_v15
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: zai-org/GLM-5-FP8
model_size: 31B
ranking_group: single
us_pacific_date: 2026-03-26
win_ratio: 0.5686448184233835
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['####', '<|im_start|>', '<|assistant|>', '</s>', '<|im_end|>', 'You:'], 'max_input_tokens': 1500, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': "[gMASK]<sop><|system|>\n{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '<|assistant|>\n{bot_name}: {message}', 'user_template': '<|user|>\n{message}', 'response_template': '<|assistant|></think>{bot_name}:', 'truncate_by_message': False}
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
Pipeline stage vllm_upload skipped, reason=amd cluster
Pipeline stage VLLMUploader completed in 0.19s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Starting job with name zai-org-glm-5-fp8-v15-uploader-amd
Waiting for job on zai-org-glm-5-fp8-v15-uploader-amd to finish
2026-03-26T21:35:53.418595+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:36:53.645993+00:00 monitor updated for zai-org-glm-5-fp8_v15
zai-org-glm-5-fp8-v15-uploader-amd: Using quantization_mode: none
zai-org-glm-5-fp8-v15-uploader-amd: Downloading snapshot of zai-org/GLM-5-FP8...
2026-03-26T21:37:53.867730+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:38:54.086543+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:39:54.320709+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:40:54.536295+00:00 monitor updated for zai-org-glm-5-fp8_v15
zai-org-glm-5-fp8-v15-uploader-amd: Downloaded in 246.202s
2026-03-26T21:41:54.755630+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:42:54.967601+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:43:55.184632+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:44:55.405585+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:45:55.640168+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:46:55.881267+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:47:56.100494+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:48:56.317251+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:49:56.614372+00:00 monitor updated for zai-org-glm-5-fp8_v15
zai-org-glm-5-fp8-v15-uploader-amd: Processed model zai-org/GLM-5-FP8 in 780.017s
zai-org-glm-5-fp8-v15-uploader-amd: creating bucket guanaco-vllm-models
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
zai-org-glm-5-fp8-v15-uploader-amd: RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
zai-org-glm-5-fp8-v15-uploader-amd: RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
zai-org-glm-5-fp8-v15-uploader-amd: invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
zai-org-glm-5-fp8-v15-uploader-amd: invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
zai-org-glm-5-fp8-v15-uploader-amd: if re.search("-\.", bucket, re.UNICODE):
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
zai-org-glm-5-fp8-v15-uploader-amd: if re.search("\.\.", bucket, re.UNICODE):
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
zai-org-glm-5-fp8-v15-uploader-amd: _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
zai-org-glm-5-fp8-v15-uploader-amd: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
zai-org-glm-5-fp8-v15-uploader-amd: wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
zai-org-glm-5-fp8-v15-uploader-amd: Bucket 's3://guanaco-vllm-models/' created
zai-org-glm-5-fp8-v15-uploader-amd: uploading /dev/shm/model_output to s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/generation_config.json
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/README.md
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/config.json
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/chat_template.jinja
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/.gitattributes
2026-03-26T21:50:56.842355+00:00 monitor updated for zai-org-glm-5-fp8_v15
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/tokenizer.json
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00142-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00142-of-00142.safetensors
2026-03-26T21:51:57.051407+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:52:57.266820+00:00 monitor updated for zai-org-glm-5-fp8_v15
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00008-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00008-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00039-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00039-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00006-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00006-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00023-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00023-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00004-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00004-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00024-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00024-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00042-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00042-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00091-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00091-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00040-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00040-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00051-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00051-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00050-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00050-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00140-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00140-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00044-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00044-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00013-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00013-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00072-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00072-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00027-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00027-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00073-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00073-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00031-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00031-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00015-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00015-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00034-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00034-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00053-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00053-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00041-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00041-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00043-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00043-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00038-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00038-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00028-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00028-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00132-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00132-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00030-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00030-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00016-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00016-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00054-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00054-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00055-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00055-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00026-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00026-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00089-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00089-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00001-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00001-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00060-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00060-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00033-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00033-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00056-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00056-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00076-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00076-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00127-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00127-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00048-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00048-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00071-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00071-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00064-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00064-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00005-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00005-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00022-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00022-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00070-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00070-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00007-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00007-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00128-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00128-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00094-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00094-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00009-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00009-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00019-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00019-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00110-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00110-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00017-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00017-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00093-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00093-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00112-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00112-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00081-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00081-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00075-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00075-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00046-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00046-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00058-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00058-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00109-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00109-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00106-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00106-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00018-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00018-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00085-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00085-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00066-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00066-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00083-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00083-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00079-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00079-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00074-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00074-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00049-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00049-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00078-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00078-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00086-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00086-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00139-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00139-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00037-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00037-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00011-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00011-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00003-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00003-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00010-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00010-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00119-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00119-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00032-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00032-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00092-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00092-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00036-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00036-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00101-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00101-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00118-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00118-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00087-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00087-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00082-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00082-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00141-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00141-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00045-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00045-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00116-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00116-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00090-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00090-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00125-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00125-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00062-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00062-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00097-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00097-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00069-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00069-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00103-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00103-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00061-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00061-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00135-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00135-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00120-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00120-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00077-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00077-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00099-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00099-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00084-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00084-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00134-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00134-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00088-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00088-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00068-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00068-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00111-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00111-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00095-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00095-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00080-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00080-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00121-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00121-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00108-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00108-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00029-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00029-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00137-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00137-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00124-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00124-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00002-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00002-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00065-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00065-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00113-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00113-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00138-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00138-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00117-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00117-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00126-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00126-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00130-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00130-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00102-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00102-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00098-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00098-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00107-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00107-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00133-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00133-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00052-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00052-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00057-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00057-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00100-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00100-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00123-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00123-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00136-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00136-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00104-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00104-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00131-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00131-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00025-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00025-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00129-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00129-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00122-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00122-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00114-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00114-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00067-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00067-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00096-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00096-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00115-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00115-of-00142.safetensors
zai-org-glm-5-fp8-v15-uploader-amd: cp /dev/shm/model_output/model-00105-of-00142.safetensors s3://guanaco-vllm-models/zai-org-glm-5-fp8-v15/amd/model-00105-of-00142.safetensors
2026-03-26T21:53:57.484465+00:00 monitor updated for zai-org-glm-5-fp8_v15
Job zai-org-glm-5-fp8-v15-uploader-amd completed after 1164.64s with status: succeeded
Stopping job with name zai-org-glm-5-fp8-v15-uploader-amd
Pipeline stage VLLMUploaderAMD completed in 1166.04s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 1.63s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service zai-org-glm-5-fp8-v15
Waiting for inference service zai-org-glm-5-fp8-v15 to be ready
2026-03-26T21:54:57.718389+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:55:57.971585+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:56:58.291400+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:57:58.611162+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:58:58.974173+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T21:59:59.293575+00:00 monitor updated for zai-org-glm-5-fp8_v15
2026-03-26T22:00:59.586685+00:00 monitor updated for zai-org-glm-5-fp8_v15
Inference service zai-org-glm-5-fp8-v15 ready after 427.10260462760925s
Pipeline stage VLLMDeployer completed in 429.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.243609189987183s
Received healthy response to inference request in 3.47105073928833s
Received healthy response to inference request in 3.2071163654327393s
Received healthy response to inference request in 4.744729518890381s
Received healthy response to inference request in 2.8445210456848145s
Received healthy response to inference request in 3.4368622303009033s
Received healthy response to inference request in 2.4954278469085693s
2026-03-26T22:01:59.915380+00:00 monitor updated for zai-org-glm-5-fp8_v15
Received healthy response to inference request in 2.7140750885009766s
Received healthy response to inference request in 3.103639841079712s
Received healthy response to inference request in 3.2326979637145996s
Received healthy response to inference request in 2.7684872150421143s
Received healthy response to inference request in 2.5603349208831787s
Received healthy response to inference request in 2.665870189666748s
Received healthy response to inference request in 3.2207424640655518s
Received healthy response to inference request in 3.408633232116699s
Received healthy response to inference request in 2.5463900566101074s
Received healthy response to inference request in 2.6662938594818115s
Received healthy response to inference request in 3.346158504486084s
Received healthy response to inference request in 3.2259738445281982s
Received healthy response to inference request in 3.2307639122009277s
Received healthy response to inference request in 2.841033458709717s
Received healthy response to inference request in 3.1416256427764893s
Received healthy response to inference request in 2.784298896789551s
Received healthy response to inference request in 2.5766756534576416s
Received healthy response to inference request in 3.230163335800171s
Received healthy response to inference request in 2.5141403675079346s
Received healthy response to inference request in 3.1476776599884033s
2026-03-26T22:03:00.162150+00:00 monitor updated for zai-org-glm-5-fp8_v15
Received healthy response to inference request in 2.7559738159179688s
Received healthy response to inference request in 3.283041000366211s
Received healthy response to inference request in 3.251042366027832s
30 requests
0 failed requests
5th percentile: 2.5286527276039124
10th percentile: 2.5589404344558715
20th percentile: 2.6662091255187987
30th percentile: 2.7647331953048706
40th percentile: 2.8431260108947756
50th percentile: 3.1446516513824463
60th percentile: 3.2228350162506105
70th percentile: 3.231344127655029
80th percentile: 3.2956645011901857
90th percentile: 3.4402810811996463
95th percentile: 4.171574068069455
99th percentile: 5.098934085369111
mean time: 3.1219683408737184
Pipeline stage StressChecker completed in 100.08s
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
zai-org-glm-5-fp8_v15 status is now deployed due to DeploymentManager action
zai-org-glm-5-fp8_v15 status is now inactive due to auto deactivation removed underperforming models
zai-org-glm-5-fp8_v15 status is now torndown due to DeploymentManager action