 Alexander Korolev
|
240002c125
fix(glm52): patch vLLM structured-output reasoning-boundary bug under MTP
|
há 3 meses atrás |
|
Alexander Korolev
|
dbbdc3efbf
fix(composed_model): add exclude field to skip overlay files
|
há 3 meses atrás |
|
Alexander Korolev
|
2a72c806e4
fix(recipe): exclude 5 mis-packed layers from NF4 Lloyd decode set
|
há 3 meses atrás |
|
Alexander Korolev
|
de18759712
feat(serve): add composed_model for multi-repo model directories
|
há 3 meses atrás |
|
Alexander Korolev
|
51ed390d64
refactor(recipe): use relative symlinks instead of rsync for NF4 expert overlay
|
há 3 meses atrás |
|
Alexander Korolev
|
8419efeb18
fix(recipe): correct NF4 Lloyd env vars after kernel source inspection
|
há 3 meses atrás |
|
Alexander Korolev
|
70ff8fda18
feat(recipe): add GLM-5.2 NF4 Lloyd-Experts-GPTQ recipe, bump glm52 image to 1.4
|
há 3 meses atrás |
