Jiajun Li 3ad61b8df7 docs(score-centering): name the router that supports the recipe (#3904)

2026-10-03 14:44:46 -07:00

..

geo3k-vlm

build: retire CUDA 12 Docker builds (#3895)

2026-10-02 11:26:28 -07:00

infra-features

docs(score-centering): name the router that supports the recipe (#3904)

2026-10-03 14:44:46 -07:00

on-policy-distillation

docs: mirror examples/ READMEs into the Examples tab (#2481)

2026-08-12 15:26:43 -07:00

geo3k-vlm.md

build: retire CUDA 12 Docker builds (#3895)

2026-10-02 11:26:28 -07:00

index.md

Document score-centering configuration and supported sampling (#3626)

2026-10-03 00:23:15 -07:00

infra-features.md

docs: label-only sidebar groups, explicit Overview pages, scoped link color (#2489)

2026-08-13 14:20:23 -07:00

multi-lora.md

Unify HF snapshot and checkpoint writing (#3198)

2026-09-23 18:22:35 -07:00

multi-policy.md

Make the multi policy demo a runnable example the tests import (#2998)

2026-09-26 20:07:18 +08:00

on-policy-distillation.md

docs: mirror examples/ READMEs into the Examples tab (#2481)

2026-08-12 15:26:43 -07:00

ppo.md

Make the cell based train group the only trainer implementation (#2154)

2026-09-04 14:45:06 +08:00

retool-v2.md

docs: mirror examples/ READMEs into the Examples tab (#2481)

2026-08-12 15:26:43 -07:00

swe-agent-harbor-docker.md

Let agents outside the cluster reach session servers on more than one host (#2851)

2026-09-24 17:19:11 -07:00