* [ci] upload several tests

* [ci] add sanity and tensordict utility workflow

* [ci] fix workflow

* try fix import ci

* [dataproto] update repeat and unpad/pad

* fix rollout test to 2GPU

* add a fsdp vllm hybridengine script, which can be launched by torchrun

* fix import test

* update requirement.txt

* draft vllm fsdp test

* update label

* fix

* upload conda

* test conda

* test ci

* use docker

* test ci

* test ci

* test ci

* update ci

* test ci

* fix model loader

* fix model loader

* test ci

* test

* upload e2e digit completion test

* update running script for e2e test

* update test config

* fix path

* test

* fix import to register autotokenizer

* fix tokenizer

* fix create dataset

* fix

* fix reward model validate

* fix reward module of digit_completion

* fix reward module of digit_completion

* fix reward module of digit_completion

* fix reward module of digit_completion

* fix reward module of digit_completion

* can run but seems to have some test issue

* no problem, add check results

* add e2e training

* l20-0 seems has docker permission problem, test later

* fix

* test l20-0 and torchrun

* test l20-0 and torchrun

* fix

* fix

* fix

* fix

* fix

* tolerate difference

* tolerate difference with levenshtein

* lint

* add more test for ray

* delete

* use docker on l20

* use docker on l20

* add upgrade

* update ci

* delete code

* ignore test

* upgrade ray

* fix workerhelper method

* lint

* revert worker changes

* fix

* fix

* fix

* fix worker missing func