Alexander Korolev
|
1ba1d99e05
fix: resolve review findings across modules
|
3 meses atrás |
Alexander Korolev
|
4767f6fe4d
docs(agents): warn that cluster may be serving live before stop/power off
|
3 meses atrás |
Alexander Korolev
|
b5905ac702
docs(agents): clarify path-ref resolves to container-side HF cache path
|
3 meses atrás |
Alexander Korolev
|
a7cd759af1
feat(recipe): model-subfolder path refs via {{name}} substitution
|
3 meses atrás |
Alexander Korolev
|
6cd245f9a8
feat(recipe): model-subfolder mounts resolved per-node from HF cache
|
3 meses atrás |
Alexander Korolev
|
2b0deeaffa
feat(recipe): extra_mounts with config alias resolution + tilde + env injection
|
3 meses atrás |
Alexander Korolev
|
12f1fa44f9
feat!: rename binary from sm121-launcher to sm121
|
3 meses atrás |
Alexander Korolev
|
acadda1259
feat: auto-sync Docker image (ANY source node) + --sync-image / --sync-image-source flags
|
3 meses atrás |
Alexander Korolev
|
6081ccf443
feat: mods system — entrypoint wrapping + global/recipe mods with volume mount
|
4 meses atrás |
Alexander Korolev
|
ce60c5c59f
feat: serve follows logs by default, returns Cluster for follow-up
|
4 meses atrás |
Alexander Korolev
|
30efdff974
docs: restructure for end users: DEVELOPMENT.md + user-friendly README
|
4 meses atrás |
Alexander Korolev
|
66a06964de
docs: update AGENTS.md and README.md to match current implementation
|
4 meses atrás |
Alexander Korolev
|
ce40c23b7a
feat: section aliases for exec subcommand
|
4 meses atrás |
Alexander Korolev
|
bfe94fa39e
feat: pre-serve hooks + exec subcommand for cluster mass-execution
|
4 meses atrás |
Alexander Korolev
|
303e0ce9be
feat: SGLang engine support + minimax-m3 recipe + README
|
4 meses atrás |
Alexander Korolev
|
750a89980c
refactor: integrate health.rs, deduplicate select_cluster, fix Ray backend, add 21 tests
|
4 meses atrás |
Alexander Korolev
|
ff2838f901
feat: tmux launch variant with sequential Ray startup, deep health checks, multi-window layout
|
4 meses atrás |
Alexander Korolev
|
8db6d414a3
refactor: comprehensive rewrite — concurrent SSH, labels, config-driven clusters, host key verification
|
6 meses atrás |
Alexander Korolev
|
491d7a66f6
Initial commit: sm121-launcher — DGX Spark cluster launcher for vLLM/SGLang
|
6 meses atrás |