 Alexander Korolev
|
09ac2dc3c4
fix(deepseek-v4-flash): revert wrong tp pp changes
|
hace 4 meses |
|
Alexander Korolev
|
746049fc18
fix(cli): switch clap help texts to English
|
hace 4 meses |
|
Alexander Korolev
|
aa34a575e4
fix(i18n): wire up unused Fluent keys in before_serve, host_keys, health, exec
|
hace 4 meses |
|
Alexander Korolev
|
f55cd70082
refactor: replace #[allow] with structs for start_cluster and build_docker_command
|
hace 4 meses |
|
Alexander Korolev
|
ce60c5c59f
feat: serve follows logs by default, returns Cluster for follow-up
|
hace 4 meses |
|
Alexander Korolev
|
e84b676397
feat: serve follows logs by default, --no-follow to skip
|
hace 4 meses |
|
Alexander Korolev
|
d6ccc9af9a
fix: use docker stop only, no rm step
|
hace 4 meses |
|
Alexander Korolev
|
be65b44ddb
fix: stop containers in single rm -f step
|
hace 4 meses |
|
Alexander Korolev
|
6ff1e710aa
feat: record cluster label on containers for auto-detection
|
hace 4 meses |
|
Alexander Korolev
|
d05805c577
feat: add --cluster to docker stop and logs commands
|
hace 4 meses |
|
Alexander Korolev
|
ef03b8c784
feat: auto-scale PP when pipeline_parallel_size == required_nodes
|
hace 4 meses |
|
Alexander Korolev
|
04413a8991
feat: auto-scale TP when recipe runs on larger cluster
|
hace 4 meses |
|
Alexander Korolev
|
25540b4f48
fix: allow recipe with fewer required_nodes to run on larger cluster
|
hace 4 meses |
|
Alexander Korolev
|
b5615f604d
fix(recipe): switch GLM-5.2 from SGLang to vLLM
|
hace 4 meses |
|
Alexander Korolev
|
3d35c82535
feat(recipe): add GLM-5.2 NVFP4 recipe (4-node SGLang)
|
hace 4 meses |
|
Alexander Korolev
|
8f000e671a
fix(ssh): separate ssh_session_follow with no inactivity timeout
|
hace 4 meses |
|
Alexander Korolev
|
9d54d3f94c
gemma4-12b: working recipe with distributed_backend=none
|
hace 4 meses |
|
Alexander Korolev
|
03c293c4ca
refactor(docker): move health_check to submodule
|
hace 4 meses |
|
Alexander Korolev
|
71855e9f45
feat(recipe): add Gemma 4 12B IT (MTP) recipe + --node flag for single-node serve
|
hace 4 meses |
|
Alexander Korolev
|
17a4f0c39a
feat(i18n): localize all remaining module output strings
|
hace 4 meses |
|
Alexander Korolev
|
5019c1cb34
feat(i18n): localize doctor module output messages
|
hace 4 meses |
|
Alexander Korolev
|
3d12b851cd
fix: default RUST_LOG=info when env var is unset
|
hace 4 meses |
|
Alexander Korolev
|
15b97e42fd
fix(i18n): normalize LANG from 'ru_RU.UTF-8' to 'ru-RU' for unic-langid
|
hace 4 meses |
|
Alexander Korolev
|
53edb54fe8
fix(i18n): check LANG env var for locale (macOS compat)
|
hace 4 meses |
|
Alexander Korolev
|
cb4c15ec7a
fix: add 5s SSH connect timeout to prevent hangs on offline nodes
|
hace 4 meses |
|
Alexander Korolev
|
30efdff974
docs: restructure for end users: DEVELOPMENT.md + user-friendly README
|
hace 4 meses |
|
Alexander Korolev
|
d455c29d37
chore: remove stale .hermes/plans directory
|
hace 4 meses |
|
Alexander Korolev
|
66a06964de
docs: update AGENTS.md and README.md to match current implementation
|
hace 4 meses |
|
Alexander Korolev
|
127c82cde8
fix(i18n): use CLDR plural rules in all locale files
|
hace 4 meses |
|
Alexander Korolev
|
c54d12d7cc
test: verify Russian pluralization (узел/узла/узлов) via Fluent CLDR
|
hace 4 meses |
