[misc] feat: prototype deprecate DataProto and replace with Tensordict: part 1

requirements-npu.txt

@@ -10,7 +10,7 @@ peft>=0.15.2
 pyarrow>=15.0.0
 pybind11
 pylatexenc
-tensordict>=0.8.0,<=0.9.1,!=0.9.0
+tensordict>=0.8.0,<=0.10.0,!=0.9.0
 transformers==4.52.4
 ray==2.46.0
 wandb

requirements.txt

@@ -14,7 +14,7 @@ pybind11
 pylatexenc
 pre-commit
 ray[default]
-tensordict>=0.8.0,<=0.9.1,!=0.9.0
+tensordict>=0.8.0,<=0.10.0,!=0.9.0
 torchdata
 transformers
 # vllm==0.8.4

requirements_sglang.txt

@@ -12,7 +12,7 @@ pyarrow>=19.0.0
 pybind11
 pylatexenc
 ray[default]>=2.10
-tensordict>=0.8.0,<=0.9.1,!=0.9.0
+tensordict>=0.8.0,<=0.10.0,!=0.9.0
 torchdata
 torchvision
 transformers

setup.py

@@ -37,7 +37,7 @@
     "pylatexenc",
     "ray[default]>=2.41.0",
     "torchdata",
-    "tensordict>=0.8.0,<=0.9.1,!=0.9.0",
+    "tensordict>=0.8.0,<=0.10.0,!=0.9.0",
     "transformers",
     "wandb",
     "packaging>=20.0",
@@ -49,9 +49,9 @@
 GEO_REQUIRES = ["mathruler", "torchvision", "qwen_vl_utils"]
 GPU_REQUIRES = ["liger-kernel", "flash-attn"]
 MATH_REQUIRES = ["math-verify"]  # Add math-verify as an optional dependency
-VLLM_REQUIRES = ["tensordict>=0.8.0,<=0.9.1,!=0.9.0", "vllm>=0.7.3,<=0.9.1"]
+VLLM_REQUIRES = ["tensordict>=0.8.0,<=0.10.0,!=0.9.0", "vllm>=0.7.3,<=0.9.1"]
 SGLANG_REQUIRES = [
-    "tensordict>=0.8.0,<=0.9.1,!=0.9.0",
+    "tensordict>=0.8.0,<=0.10.0,!=0.9.0",
     "sglang[srt,openai]==0.4.10.post2",
     "torch==2.7.1",
 ]

tests/special_sanity/validate_structure.py

@@ -86,7 +86,11 @@ def main() -> None:
     parser.add_argument(
         "--allow-files",
         nargs="*",
-        default=["tests/test_protocol_on_cpu.py", "tests/test_base_config_on_cpu.py"],
+        default=[
+            "tests/test_protocol_on_cpu.py",
+            "tests/test_base_config_on_cpu.py",
+            "tests/test_protocol_v2_on_cpu.py",
+        ],
         help="Extra top-level test folders that are exempt from the rule",
     )
     args = parser.parse_args()

tests/test_protocol_on_cpu.py

@@ -16,7 +16,9 @@
 
 import numpy as np
 import pytest
+import tensordict
 import torch
+from packaging.version import parse as parse_version
 from tensordict import TensorDict
 
 from verl import DataProto
@@ -598,3 +600,17 @@ def test_dataproto_chunk_after_index():
     selected = data[torch_int_mask]
     assert isinstance(selected.batch.batch_size, torch.Size)
     assert all(isinstance(d, int) for d in selected.batch.batch_size)
+
+
+@pytest.mark.skipif(
+    parse_version(tensordict.__version__) < parse_version("0.10"), reason="requires at least tensordict 0.10"
+)
+def test_to_tensordict():
+    obs = torch.tensor([1, 2, 3, 4, 5, 6])
+    labels = ["a", "b", "c", "d", "e", "f"]
+    data = DataProto.from_dict(tensors={"obs": obs}, non_tensors={"labels": labels}, meta_info={"name": "abdce"})
+    output = data.to_tensordict()
+
+    assert torch.all(torch.eq(output["obs"], obs)).item()
+    assert output["labels"] == labels
+    assert output["name"] == "abdce"