 Alexander Korolev
|
4a706d5739
audit: DFlash2 A/B blocked — eugr build rejects all draft attention backends under fp8 KV (4 backends tried); DFlash-for-GLM is a kindling-overlay capability; cross-option blocked by the lossless scale format
|
5 dagar sedan |
|
Alexander Korolev
|
7ba7dde55b
audit: GLM 2x fully resolved through the launcher — missing distributed_backend (independent full-model loads = the 4 stalls), global-vs-local node-rank, cold GMU floor; lane now runlock-tracked and boots in ~4 min
|
5 dagar sedan |
|
Alexander Korolev
|
fd84b405e5
audit: GLM 2x lane RESOLVED via the card's manual flow — routing passed 42/42 (launcher died at 7/42), bench 92/100 ★★★★★; launcher-integration delta bisect is the remaining work item
|
5 dagar sedan |
|
Alexander Korolev
|
2ce7181660
audit: GLM 2x stall #4 — checkpoint on node-local NVMe (mirror content-verified) still freezes the head during b12x shard routing; NFS-page-cache hypothesis dead, routing-phase UMA exhaustion intrinsic on 2x121GB; mirror completeness fix shipped (59291f3)
|
5 dagar sedan |
|
Alexander Korolev
|
4bc842cd8a
audit: DeepSeek-V4.1-Flash-1017 vs Aiden SGLang 1.7.1 image — protocol encoder is jinja-free (tool-parser-keyed), DSML markers byte-identical; one real regression (REASONING_EFFORT_MAPPINGS shifted a tier: image 25/50/75/100 vs 1017 50/75/100); TC-89 verdict contradicts its own milestones (grader flake), TC-92 recurring DS4.1 disclosure gap; GLM 2x stall root-cause refined (card requires node-local checkpoint; mirror copy incomplete 41/42 + launcher partial-mirror check hole)
|
6 dagar sedan |
