Comparing 94b72eadf3...da5b9f8612 - xc_validation_strategy_vllm_zhouyuanxi - Gitea: Git with a cup of tea

zhouyuanxi/xc_validation_strategy_vllm_zhouyuanxi

Author	SHA1	Message	Date
zhouyuanxi	da5b9f8612	restore all 10 accounts to ACCOUNTS; gate the active submitters behind ACTIVE_ACCOUNT_LABELS The six accounts dropped in v1.1.0 are back in ACCOUNTS so their tokens are not lost. Which ones actually submit is now controlled by ACTIVE_ACCOUNT_LABELS, currently the four requested for this round; set it to [] to rotate over all ten. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-20 17:20:28 +08:00
zhouyuanxi	e088e90dda	submit 1366 models from the relaxed filter, round-robin across 4 accounts Filter condition 2 relaxed from "verified on another card" to "verified OR verifying on another card": a model already under verification elsewhere has passed the platform's basic checks, it just has no result yet. Same candidate pool yields 1366 instead of 12 (114x) - the two original conditions are近乎 mutually exclusive, since a model verified on another card has long since been tried on every card. Account handling changed from sequential fallback to round-robin over zhangyuanxi / jiajing / l112233 / l11223344, so the four share the load evenly (verified: 342/342/341/341) instead of piling onto the first account until it hits 60007. Iluvatar_bi-150 is back in GPU_JOBS now that a vllm iluvatar image is configured. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-20 17:15:54 +08:00
zhouyuanxi	6d2b055ee4	submit round-33 filter results: MetaX_c-500(2)/Kunlunxin_p-800(3)/hygon_k100-ai(1)/Cambricon_mlu-370-x8(3)/Biren_166m(2), 11 models total Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-20 15:34:48 +08:00
zhouyuanxi	cea3a081c7	submit round-30 filter results: MetaX_c-500(23)/Kunlunxin_p-800(3)/hygon_k100-ai(26)/Cambricon_mlu-370-x8(7)/Biren_166m(18), 77 models total Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-18 16:27:25 +08:00
zhouyuanxi	e66f3d02cb	submit round-28 filter results: MetaX_c-500(5)/Kunlunxin_p-800(4)/hygon_k100-ai(2)/Cambricon_mlu-370-x8(4)/Biren_166m(1), 16 models total Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-17 14:51:40 +08:00
zhouyuanxi	2d02030d50	submit round-26 filter results: MetaX_c-500(5)/Kunlunxin_p-800(1)/hygon_k100-ai(1)/Cambricon_mlu-370-x8(1)/Biren_166m(3), 11 models total Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-16 13:38:42 +08:00
zhouyuanxi	1c29242290	submit round-25 filter results: MetaX_c-500(8)/Kunlunxin_p-800(19)/hygon_k100-ai(40)/Cambricon_mlu-370-x8(16)/Biren_166m(1), 84 models total Restores hygon_k100-ai to GPU_JOBS; its list was emptied in v1.0.31 for the zhoushasha resubmission round. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-09-15 18:13:40 +08:00

1 changed files with 1437 additions and 175 deletions

1612

main.py

View File

File diff suppressed because it is too large Load Diff