Alexander Korolev
|
d806bd2c2f
aiden 4x: use the extended image (production-1.2 + instanttensor), restore instanttensor load
|
1 mês atrás |
Alexander Korolev
|
9e55382f40
aiden 4x: drop --load-format instanttensor (not in production-1.2 image)
|
1 mês atrás |
Alexander Korolev
|
bbe82a903e
aiden 4x un-deferred: production-1.2 image, zai FP8 weights now cached
|
1 mês atrás |
Alexander Korolev
|
d31e3b0b0c
glm53 aiden: local image (prod-1.1 + instanttensor), MTP spec, 512K ctx
|
1 mês atrás |
Alexander Korolev
|
2b52f97ac3
aiden lanes: drop manual HF mounts (launcher auto-mounts ~/.cache/huggingface = shared NAS on all 4 nodes); GLM 4x -> NVFP4 (in shared cache, +23% vs FP8)
|
1 mês atrás |
Alexander Korolev
|
a0c57b9e2f
aiden lanes: entrypoint=[] for built-in-entrypoint images (launcher doubles CMD otherwise); vision 2x uses proven overlay img + aiden DSpark-greedy additions (his env-script needs a dedicated pass)
|
1 mês atrás |
Alexander Korolev
|
ce4727d2a3
aiden lanes: 2x+4x recipes from aidenle.com guides (glm prod-1.1 DFlash2-7 + dsv4 vision prod-3.72 DSpark-6); 2x to verify, 4x deferred (FP8 ckpt downloading)
|
1 mês atrás |