Alexander Korolev
|
08d1e9fe03
feat(serve): add --mirror — serve from a per-node local HF mirror
|
2 месяцев назад |
Alexander Korolev
|
d2026c2ddf
feat(deepseek-v4): raise max-model-len to 1M + pin KV cache bytes (eugr)
|
2 месяцев назад |
Alexander Korolev
|
3aa9d380b2
feat(recipes): agent-serving profile + GMU/env fixes from benchmark findings
|
2 месяцев назад |
Alexander Korolev
|
a8e4932fc4
feat(deepseek-v4): add eugr b12x recipe variant with baked draft-loader mod
|
2 месяцев назад |