[misc] feat: Added: "tensorboard" to the requirements.txt (#2900)

### What does this PR do?

> This PR adds tensorboard as a dependency to requirements.txt file,
across several Dockerfiles (Dockerfile.ngc.vllm, Dockerfile.ngc.vllm0.8,
Dockerfile.ngc.vllm0.8.sagemaker), a setup script
(install_vllm_sglang_mcore.sh), and the main setup.py file. This change
ensures that the tensorboard package is consistently installed, enabling
visualization of training metrics for various configurations and
deployment environments. This is a maintenance task that enhances the
project's observability without altering core functionality.

### Test

> This change is a dependency update and doesn't require specific
testing beyond confirming the installation is successful.

### API and Usage Example

> No API changes are introduced. The usage of TensorBoard would be
initiated by the user after installing the requirements.

```python
# No code snippet is applicable for this change

docker/Dockerfile.ngc.vllm

@@ -35,7 +35,8 @@ RUN pip3 install --no-cache-dir \
     'tensordict<0.6' \
     'transformers' \
     'vllm==0.6.3.post1' \
-    'wandb'
+    'wandb' \
+    'tensorboard'
 
 # full dependencies
 RUN pip3 install pytest pre-commit py-spy pyext liger-kernel

docker/Dockerfile.ngc.vllm0.8

@@ -51,7 +51,7 @@ RUN pip install --no-cache-dir "vllm==0.8.3" "torch==2.6.0" "torchvision==0.21.0
     "transformers[hf_xet]>=4.51.0" accelerate datasets peft hf-transfer \
     "numpy<2.0.0" "pyarrow>=15.0.0" pandas \
     ray[default] codetiming hydra-core pylatexenc qwen-vl-utils wandb dill pybind11 liger-kernel mathruler \
-    pytest py-spy pyext pre-commit ruff
+    pytest py-spy pyext pre-commit ruff tensorboard
 
 # Install flash-attn-2.7.4.post1 (cxx11abi=False)
 RUN wget -nv https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl && \

docker/Dockerfile.ngc.vllm0.8.sagemaker

@@ -27,7 +27,7 @@ RUN apt-get update && \
 RUN pip install --no-cache-dir vllm==0.8.2 torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 tensordict torchdata==0.11.0 \
     transformers>=4.49.0 accelerate datasets peft hf-transfer \
     ray[default] codetiming hydra-core pandas pyarrow>=15.0.0 pylatexenc qwen-vl-utils wandb dill pybind11 liger-kernel mathruler \
-    pytest pre-commit py-spy pyext ruff
+    pytest pre-commit py-spy pyext ruff tensorboard
 
 # Install flash_attn-2.7.4.post1
 RUN pip uninstall -y transformer-engine flash-attn && \

requirements.txt

@@ -24,3 +24,4 @@ uvicorn
 fastapi
 latex2sympy2_extended
 math_verify
+tensorboard

scripts/install_vllm_sglang_mcore.sh

@@ -15,7 +15,7 @@ echo "2. install basic packages"
 pip install "transformers[hf_xet]>=4.51.0" accelerate datasets peft hf-transfer \
     "numpy<2.0.0" "pyarrow>=15.0.0" pandas \
     ray[default] codetiming hydra-core pylatexenc qwen-vl-utils wandb dill pybind11 liger-kernel mathruler \
-    pytest py-spy pyext pre-commit ruff
+    pytest py-spy pyext pre-commit ruff tensorboard 
 
 pip install "nvidia-ml-py>=12.560.30" "fastapi[standard]>=0.115.0" "optree>=0.13.0" "pydantic>=2.9" "grpcio>=1.62.1"
 

setup.py

@@ -41,6 +41,7 @@ install_requires = [
     "transformers",
     "wandb",
     "packaging>=20.0",
+    "tensorboard",
 ]
 
 TEST_REQUIRES = ["pytest", "pre-commit", "py-spy", "pytest-asyncio"]