* [BREAKING][core] move single_controller into verl directory

* fix blocking flag in fsdp workers

* [example] add a split placement tutorial

* lint

* [distro] feat: add docker support

* update docker tag

* update description

* [feat] support vllm spmd version in v0.6.3

* [misc] fix hf_weight loader

* [misc] rollout: update vllm version and fix hf import

* lint

* [misc] fix init

* [doc] feat: modify doc to support vllm v6

* [tokenizer] feat: support tokenizers whose pad_token_id is none

* add test to ci

* install test version

* update ci

* dont use gemma for testing

* dont use gemma for testing

* add proxy

* revert dataset test

* add back tests

* fix format

* fix format

* fix deps

* use git clone instead of https download

* fix path

* revert and use one yaml for gpu instead

* fix path

* cleanup

* limit pyarrow version

* Revert "limit pyarrow version"

This reverts commit b924f79a79088c21636269d11a4ec3095af10c09.

* lfs

* try lfs

* do not clone if exist

* [deps] fix: make wandb optional dependency

* allow ppo scripts to take additional args

* fix lint

* [ci] add linting tests dir

* delete redundant tests

* [ci] change test gpu usage to 2

* [ci] update check ci

* [ci] fix init

* [ci] fix ray test running machine

* [ci] test self-hosted gpu

* [ci] fix yapf lint ci

* [ci] test checkout

* [ci] test origin

* [ci] fix ray test

* [ci] fix ray test

* [ci] add install verl in ray

* [fix] fix some bugs related to hf_weight_loader

* [doc] fix doc typo

* [ci] fix github action

* [ci] lint

* [doc] fix typo

* [misc] add small scale gemma2-2b example for debug

* [misc] fix: add eval() and train() for gradient checkpoint

* Update base.py

* Update base.py

* update

Signed-off-by: Kai-Hsun Chen <kaihsun@anyscale.com>

---------

Signed-off-by: Kai-Hsun Chen <kaihsun@anyscale.com>

* [ci] update some tests for hybrid programming model

* [ci] update detached worker tests

* [doc]fix: typo in fsdp dtensor weight loader extension

* [misc] fix: vllm gpu executor issue when world_size is 1

* [misc] update tutorial for opensource version

* fix deleted item

* clear output

* [misc] fix: fix pypi package missing of megatron model and fix torchrun issue

* lint

* fix sft script

* update version

* [doc] fix: delete deprecated element in config doc

* update readme to fix url

* [release] update verl doc url and update version and setup

* fix init with only fsdp and update setup for pypi

* update version