| .. |
|
Dockerfile
|
240002c125
fix(glm52): patch vLLM structured-output reasoning-boundary bug under MTP
|
hace 2 meses |
|
build.sh
|
3fa8ac759b
builds: persistent per-node buildkit cache (buildx --cache-from/to, mode=max) so version-independent apt/torch/CUDA stages are reused across recipes
|
hace 1 mes |
|
patch-structured-output.py
|
240002c125
fix(glm52): patch vLLM structured-output reasoning-boundary bug under MTP
|
hace 2 meses |