Specify the IP address when calling the bind method.

Now APIs can be displayed: 


![image](https://github.com/user-attachments/assets/6592ce68-7bf6-46cb-8dd3-a5fa6cd99f3e)

Because of the ongoing updates in vLLM, I noticed that veRL currently
cannot integrate with the nightly build of vLLM directly. The new DP
feature in the nightly version can no longer be bypassed by simply
adjusting the `data_parallel_size` parameter, and resolving this
requires further investigation.

As a temporary workaround, I recommend a customized installation of vLLM
if the V1 engine is required. I have updated the relevant documentation
accordingly to reflect this guidance.

Validation should not have shuffling.

This is an enhancement for the single batch strategy for
`val_dataloader`, making https://github.com/volcengine/verl/pull/353
more robust.

Add tensorboard in Tracking backends.

The user can set the environment variable TENSORBOARD_DIR to specify the
TensorBoard log path.

The current training script utilizes the same file during training and
evaluation. It is surmised that this may be incorrect.

[ckpt] replace DataLoader with StatefulDataLoader to support resume training for SequentialSampler  (#389)

Try to resolve this
[issue](https://github.com/volcengine/verl/issues/356).

As suggested by this issue discussion, I replace default DataLoader with
StatefulDataloader, which provides state_dict and load_state_dict
methods that may support resuming the iterator position of mid-epoch
checkpointing.

Thanks: @HillZhang1999

- Related issue: https://github.com/volcengine/verl/issues/189

`[36m(main_task pid=3523385)[0m ValueError: max_num_batched_tokens
(8192) is smaller than max_model_len (9216). This effectively limits the
maximum sequence length to max_num_batched_tokens and makes vLLM reject
longer sequences. Please increase max_num_batched_tokens or decrease
max_model_len.`

When enable_chunked_prefill is activated, the aforementioned issue will
be concealed. Please increase `max_num_batched_tokens` or `decrease
max_model_len`.

apis: add data proto to documentation page. use copy_to_local instead of copy_local_path_from_hdfs (#358)

- As titled

See issue: https://github.com/volcengine/verl/issues/342

#369

---------

Co-authored-by: Thom <zhangyi@zhangyideMacBook-Pro.local>

Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>

close #312 

Add support for ulysses sp for transformers >= 0.48

I've tested transformers 0.45.0, 0.46.0, 0.47.0, 0.48.0 and 0.49.0,
using sp=2 with the following script in my local env
```bash
#!/bin/bash

set -ex
VERSIONS=("4.45.0" "4.46.0" "4.47.0" "4.48.0" "4.49.0")

for version in "${VERSIONS[@]}"; do
    echo "Testing with Transformers version ${version}"
    echo "----------------------------------------"
    
    pip install "transformers==${version}"
    
    PYTHONPATH=./ torchrun --nproc_per_node=2 tests/model/test_transformers_ulysses.py
    
    echo "----------------------------------------"
    echo "Completed testing for version ${version}"
    echo ""
done
```

fix the issue[#331](https://github.com/volcengine/verl/issues/331)

Validation datasets are sent to inference engines as a whole batch,
which will schedule the memory themselves.

- [x] Remove `val_batch_size` from examples
- [x] Set default values of `val_batch_size` in configs as `null` and
add DEPRECATED comments
- [x] Add deprecation warnings about `val_batch_size` in
`_validate_config`

Tracking backend support vemlp wandb

---------

Co-authored-by: liudayuan.carrot <liudayuan.carrot@bytedance.com>

Implement RLOO algorithm according to https://arxiv.org/abs/2402.14740

This PR adds Ray Serve to the requirements to enable support for
multi-node training. It addresses the issue described here:
https://github.com/volcengine/verl/issues/87#issuecomment-2659493418

Co-authored-by: Yu Feng <fengyufengyu@didiglobal.com>

Support Qwen2 Megatron backend

The code is primarily adapted from the llama folder, with modifications
to use QKV bias and remove the rope_scaling of RoPE in
`verl/models/qwen2/megatron/layers/parallel_attention.py`.

- Train using Qwen2-7B-Instruct with PPO, GSM8k score can reach 0.87 at
step 75.
- not support saver now

A working Slurm example adapted from
https://docs.ray.io/en/latest/ray-core/starting-ray.html