Commit Graph
45 Commits
Author SHA1 Message Date
douya cb1c883127 Submit 385 downloaded PPU models as zhoukaile v1.0.42 2026-10-30 15:18:45 +08:00
douya 0dbfcf5684 submit first 200 no-record PPU models for zhoushasha v1.0.41 2026-10-10 11:30:43 +08:00
douya b90510acc7 submit 12 models on ppu_zw_810e for zhoushasha v1.0.40 2026-10-09 18:28:59 +08:00
douya a3d9109764 submit 338 nonquantized candidates on PPU and Hygon v1.0.39 2026-09-24 22:17:16 +08:00
douyaandClaude Opus 5 efee86e49c submit 24 models on zhoushasha: ppu_zw_810e(18)/hygon_k100-ai(4)/MetaX_c-500(1)/Biren_166m(1)
Candidate pool is the 24711 already-downloaded models, which satisfies
mechanism A's precondition that the model be present in platform storage.

Strict and relaxed condition-2 give identical results this round: of the 24007
pooled models with verify records, 24006 already have 已验证 on some card, so
relaxing to include 验证中 adds just one. The binding constraint is now how few
models lack a record on each card - Kunlunxin_p-800, Cambricon_mlu-370-x8 and
Iluvatar_bi-150 are all at zero and are left out of GPU_JOBS.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
v1.0.38
2026-09-20 18:27:33 +08:00
douyaandClaude Opus 5 793c49aea3 submit round-24 filter results on zhoushasha: MetaX_c-500(63)/Kunlunxin_p-800(1)/Cambricon_mlu-370-x8(1)/Biren_166m(95) + ppu_zw_810e(57), 217 models total
Also add a hygon_k100-ai config branch and HYGON_MODELS list (kept available but
excluded from GPU_JOBS per request). Refresh the expired AUTH_TOKEN.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
v1.0.37
2026-09-15 17:25:35 +08:00
douya d5f576fac7 submit MetaX_c-500(7) + Biren_166m(95) non-quantized models; refresh AUTH_TOKEN v1.0.36 2026-08-31 15:18:39 +08:00
douya 965783957e add self-looping quota retry: retry quota-blocked models every 30min in-process, no redeploy needed v1.0.35 2026-08-19 13:59:54 +08:00
douya cd5c7a2435 submit entire remaining ppu_zw_810e candidate pool (5424 models); run to natural quota exhaustion v1.0.34 2026-08-19 11:19:18 +08:00
douya cdbacf5a46 submit next batch of ppu_zw_810e (200 models) v1.0.33 2026-08-19 01:15:33 +08:00
douya 5bfc0fc53e submit next batch of ppu_zw_810e (200 models) v1.0.32 2026-08-19 01:07:58 +08:00
douya 606655b876 submit entire remaining ppu_zw_810e candidate pool (6220 models); run to natural quota exhaustion v1.0.31 2026-08-18 15:55:51 +08:00
douya eee9e5813c submit next batch of ppu_zw_810e (250 models, matches remaining ~2000-slot quota headroom) v1.0.30 2026-08-18 15:43:55 +08:00
douya 32122cd866 submit next batch of ppu_zw_810e (360 models, supersedes stuck v1.0.28 build) v1.0.29 2026-08-18 15:34:19 +08:00
douya ebc9f400e0 submit next batch of ppu_zw_810e (250 models); refresh AUTH_TOKEN v1.0.28 2026-08-18 11:13:33 +08:00
douya b546ad980f submit next batch of ppu_zw_810e (300 models) v1.0.27 2026-08-13 16:56:17 +08:00
douya 54adf4f956 submit next batch of ppu_zw_810e (200 models) v1.0.26 2026-08-11 14:30:02 +08:00
douya 66f378bdc0 submit next batch of ppu_zw_810e (200 models); refresh AUTH_TOKEN v1.0.25 2026-08-10 17:07:48 +08:00
douya d49bf186ae submit next batch of ppu_zw_810e (200 models) v1.0.24 2026-08-07 11:23:46 +08:00
douya 1b95e92f72 add next batch of ppu_zw_810e submission (500 models, lines 601-1100 of source list) v1.0.23 2026-08-06 13:06:23 +08:00
douya dd9db6b4d2 add ppu_zw_810e submission (600 models), refresh AUTH_TOKEN; skip other 4 GPUs this run v1.0.22 2026-08-04 20:54:10 +08:00
douya 5c9f5d9ad7 refresh all 4 GPU model lists with latest filter results v1.0.21 2026-07-29 17:36:02 +08:00
douya 9b5087467f add Kunlunxin_p-800 as 4th GPU with filtered model list v1.0.20 2026-07-29 15:16:34 +08:00
douya 7dcada5617 convert to multi-GPU submission (Biren/Cambricon/MetaX) with fresh filtered model lists v1.0.19 2026-07-29 14:26:16 +08:00
douya 5958df93b0 switch to Cambricon_mlu-370-x8 with new model list, refresh AUTH_TOKEN v1.0.18 2026-07-27 16:46:41 +08:00
douya a73274e6a4 switch back to ppu_zw_810e with new model list v1.0.17 2026-07-23 14:27:36 +08:00
douya b3c577219f switch to Biren_166m GPU with new model list v1.0.16 2026-07-22 13:53:23 +08:00
douya 1591b3050e refresh expired AUTH_TOKEN v1.0.15 2026-07-21 18:56:31 +08:00
douya 55c77faa70 update model list v1.0.14 2026-07-21 18:42:47 +08:00
douyaandClaude Fable 5 e51533e0bf update model list
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
v1.0.13
2026-07-16 16:58:36 +08:00
douya 4e603b9fb0 update v1.0.12 2026-07-14 19:06:47 +08:00
douyaandClaude Fable 5 5fe8bf27e5 update main.py
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
v1.0.11
2026-07-14 18:41:06 +08:00
douya d6b0e416db update ppu v1.0.10 2026-07-13 19:43:35 +08:00
douya 4dcfed6b6d update ppu v1.0.9 2026-07-13 18:38:55 +08:00
douya 1e8cfacd8e uodate v1.0.8 2026-06-22 19:00:46 +08:00
douya d6cca90496 update main.py v1.0.7 2026-06-22 18:44:42 +08:00
douya 031e0dc7a8 update main.py v1.0.6 2026-06-19 01:48:50 +08:00
douya af6f501a5a update main.py v1.0.5 2026-06-18 15:22:29 +08:00
douya 94da35d152 clean up Dockerfile 2026-06-14 23:55:41 +08:00
douya 5b92f129d2 clean up Dockerfile 2026-06-14 23:54:02 +08:00
douya 87d4ae1c18 fix: add env vars to Dockerfile 2026-06-12 21:02:56 +08:00
douya 6f599a8a23 fix: add env vars to Dockerfile v1.0.1 2026-06-12 14:51:50 +08:00
douya 04aa921f19 add platform strategy v1.0.0 2026-06-12 14:24:27 +08:00
douya 61df85da93 Initial commit 2026-06-10 21:45:27 +08:00
douya 0fc02e3b4f Initial commit 2026-06-10 21:42:41 +08:00