 Alexander Korolev
|
70ff8fda18
feat(recipe): add GLM-5.2 NF4 Lloyd-Experts-GPTQ recipe, bump glm52 image to 1.4
|
hai 2 meses |
|
Alexander Korolev
|
67de1f34da
refactor(build): rename docker-images/glm52-int4-int8 to glm52
|
hai 2 meses |
|
Alexander Korolev
|
febdc3b9d7
feat(build): add Solar Open2 NVFP4 recipe with recipe-pinned versions
|
hai 2 meses |
|
Alexander Korolev
|
23ae7a6484
feat(serve): add solo mode and fix single-node launch bug
|
hai 2 meses |
|
Alexander Korolev
|
65198e60fc
feat(recipe): add built-in script aliases and after_stop hook
|
hai 3 meses |
|
Alexander Korolev
|
1ba1d99e05
fix: resolve review findings across modules
|
hai 3 meses |
|
Alexander Korolev
|
ac922d02af
fix(ssh)!: harden SSH layer and refuse unpinned host keys
|
hai 3 meses |
|
Alexander Korolev
|
4767f6fe4d
docs(agents): warn that cluster may be serving live before stop/power off
|
hai 3 meses |
|
Alexander Korolev
|
7ebb007f08
feat(recipe): GLM-5.2 hf-overrides, full cudagraph compilation, adaptive spec
|
hai 3 meses |
|
Alexander Korolev
|
b5905ac702
docs(agents): clarify path-ref resolves to container-side HF cache path
|
hai 3 meses |
|
Alexander Korolev
|
dcb28faf1e
fix(docker): rewrite resolved HF cache path to container mount target
|
hai 3 meses |
|
Alexander Korolev
|
8c68124cce
feat(recipe): GLM-5.2-MXPF4-Experts-GPTQ recipe
|
hai 3 meses |
|
Alexander Korolev
|
a7cd759af1
feat(recipe): model-subfolder path refs via {{name}} substitution
|
hai 3 meses |
|
Alexander Korolev
|
6cd245f9a8
feat(recipe): model-subfolder mounts resolved per-node from HF cache
|
hai 3 meses |
|
Alexander Korolev
|
ac19fa45b8
fix(serve): dry-run skips SSH probing so it works with cluster off
|
hai 3 meses |
|
Alexander Korolev
|
2b0deeaffa
feat(recipe): extra_mounts with config alias resolution + tilde + env injection
|
hai 3 meses |
|
Alexander Korolev
|
7519fcef2a
chore(deepseek-v4-flash): disable temperature/top_p chat-template kwargs
|
hai 3 meses |
|
Alexander Korolev
|
75a7055af5
feat(glm52): build on production-hybrid-1.3 base with pinned deps
|
hai 3 meses |
|
Alexander Korolev
|
d102308e93
fix(docker): correct build alive-detection and harden build flow
|
hai 3 meses |
|
Alexander Korolev
|
d14021070c
feat(recipe): enable DFlash speculative decoding for Laguna S 2.1
|
hai 3 meses |
|
Alexander Korolev
|
e692ec1813
feat(recipe): update ghcr.io/timothystewart6/vllm-gb10 to v0.25.1-gb10.1
|
hai 3 meses |
|
Alexander Korolev
|
e844cb481a
feat(recipe): add Laguna S 2.1 NVFP4 (single-node DGX Spark)
|
hai 3 meses |
|
Alexander Korolev
|
b1a2b5f937
fix(recipe): set XDG_CACHE_HOME to /root/.cache for JIT persistence
|
hai 3 meses |
|
Alexander Korolev
|
9e28b49887
feat(recipes): add volumes support and GLM-5.2 Hybrid FP8-MXFP4 recipe
|
hai 3 meses |
|
Alexander Korolev
|
b85d797be1
feat(recipe): add GLM-5.2 Int4-Int8Mix recipe with overlay image
|
hai 3 meses |
|
Alexander Korolev
|
3f08ff868e
refactor(core): extract Docker command helpers, rewrite host_keys with toml_edit, extract per-command handlers
|
hai 3 meses |
|
Alexander Korolev
|
12f1fa44f9
feat!: rename binary from sm121-launcher to sm121
|
hai 3 meses |
|
Alexander Korolev
|
280be2c119
refactor(cli): rename --power-off to --off on stop subcommand
|
hai 3 meses |
|
Alexander Korolev
|
38d4e5568f
refactor(cli): rename --auto-power-on to --on (-O) on serve
|
hai 3 meses |
|
Alexander Korolev
|
097f22082f
feat(cli): add build subcommand for standalone image build
|
hai 3 meses |
