 Alexander Korolev
|
5a9795c612
Rebase deepseek-v4-flash :fixed overlay onto production-3.76.1
|
há 2 meses atrás |
|
Alexander Korolev
|
7f5a038adc
Tune deepseek-v4-flash-eugr: prefill threshold, prefix cache, reasoning_effort=max
|
há 2 meses atrás |
|
Alexander Korolev
|
c6eda47a99
feat(deepseek-v4-flash-eugr): use high thinking by default
|
há 2 meses atrás |
|
Alexander Korolev
|
43c9bd346f
recipe(deepseek-v4-flash-eugr): second-variant test config
|
há 2 meses atrás |
|
Alexander Korolev
|
5d90e025f0
revert: keep experimental eugr recipe changes out of main (user is still testing)
|
há 2 meses atrás |
|
Alexander Korolev
|
08d1e9fe03
feat(serve): add --mirror — serve from a per-node local HF mirror
|
há 2 meses atrás |
|
Alexander Korolev
|
d2026c2ddf
feat(deepseek-v4): raise max-model-len to 1M + pin KV cache bytes (eugr)
|
há 2 meses atrás |
|
Alexander Korolev
|
3aa9d380b2
feat(recipes): agent-serving profile + GMU/env fixes from benchmark findings
|
há 2 meses atrás |
|
Alexander Korolev
|
a8e4932fc4
feat(deepseek-v4): add eugr b12x recipe variant with baked draft-loader mod
|
há 2 meses atrás |
