lerobot-lancedb 0.1.0__tar.gz

lerobot_lancedb-0.1.0/LICENSE

@@ -0,0 +1,200 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Support. While redistributing the Work or
+      Derivative Works thereof, You may accept support, warranty,
+      indemnity, or other liability obligations and/or rights consistent
+      with this License. However, in accepting such obligations, You may
+      act only on Your own behalf and on Your sole responsibility, not on
+      behalf of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or support.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 LanceDB and lerobot-lancedb contributors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

lerobot_lancedb-0.1.0/PKG-INFO

@@ -0,0 +1,127 @@
+Metadata-Version: 2.4
+Name: lerobot-lancedb
+Version: 0.1.0
+Summary: Lance-backed datasets for LeRobot — frame-level random access on local disk and cloud (S3 / GCS / HF Hub / HF Buckets).
+Author-email: Ayush Chaurasia <ayush@lancedb.com>
+License: Apache-2.0
+Project-URL: homepage, https://github.com/lancedb/lerobot-lancedb
+Project-URL: issues, https://github.com/lancedb/lerobot-lancedb/issues
+Keywords: lerobot,lancedb,lance,robotics,datasets,dataloader
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lerobot>=0.5.0
+Requires-Dist: datasets<5.0.0,>=4.0.0
+Requires-Dist: pyarrow<30.0.0,>=21.0.0
+Requires-Dist: lancedb<1.0.0,>=0.20.0
+Requires-Dist: pylance<1.0.0,>=0.20.0
+Requires-Dist: numpy<2.3.0,>=2.0.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: torch<2.11.0,>=2.7
+Requires-Dist: torchvision>=0.22.0
+Provides-Extra: test
+Requires-Dist: pytest<9.0.0,>=8.1.0; extra == "test"
+Requires-Dist: pytest-timeout<3.0.0,>=2.4.0; extra == "test"
+Provides-Extra: dev
+Requires-Dist: lerobot-lancedb[docs,test]; extra == "dev"
+Requires-Dist: ruff>=0.14.1; extra == "dev"
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: twine>=5.1; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs>=1.6; extra == "docs"
+Requires-Dist: mkdocs-material>=9.5; extra == "docs"
+Requires-Dist: pymdown-extensions>=10.0; extra == "docs"
+Dynamic: license-file
+
+# lerobot-lancedb
+
+📖 **Docs: <https://lancedb.github.io/lerobot-lancedb/>**
+
+Lance-backed datasets for [LeRobot](https://github.com/huggingface/lerobot). Drop-in replacement for `LeRobotDataset` with two storage layouts:
+
+- **`LeRobotLanceDataset`** — per-frame JPEG bytes (lossy, fastest at single-frame access, optional GPU NVJPEG decode).
+- **`LeRobotLanceVideoDataset`** — per-file mp4 bytes stored via Lance blob v2, decoded on the fly with torchcodec. Bit-exact pixels, ~same disk size as upstream.
+
+Both subclass `LeRobotDataset` so existing trainers / samplers / `isinstance` checks accept them transparently.
+
+## Install
+
+```bash
+pip install lerobot-lancedb
+```
+
+For local development:
+
+```bash
+git clone https://github.com/lancedb/lerobot-lancedb.git
+cd lerobot-lancedb
+pip install -e '.[dev]'
+```
+
+## Quickstart
+
+```bash
+# Convert (recommended path for dtype=video sources)
+lerobot-convert-to-lance-video \
+    --repo-id=lerobot/aloha_static_cups_open \
+    --output=./aloha_cups_open_lance_video --overwrite
+```
+
+```python
+from lerobot_lancedb import LeRobotLanceVideoDataset
+ds = LeRobotLanceVideoDataset(root="./aloha_cups_open_lance_video")
+```
+
+For the JPEG layout, use `lerobot-convert-to-lance` and `LeRobotLanceDataset` instead. See the [docs](https://lancedb.github.io/lerobot-lancedb/) for the full CLI / API reference.
+
+## Benchmark
+
+Realistic training read pattern (`delta_timestamps`, 8 frames / sample, batch 32, num_workers 4, CPU decode, H100):
+
+| dataset | format | size MB | delta_ts fps | **speedup** |
+|---|---|---:|---:|---:|
+| **pusht** (96×96, 1-cam) | upstream parquet+mp4 | 7.3 | 750 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 60.0 | 3510 | **4.68×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 105.6 | 2909 | 3.88× |
+| | **`convert_to_lance_video`** | **8.0** | 2853 | **3.80×** |
+| **ALOHA cups_open** (480×640, 4-cam) | upstream parquet+mp4 | 485.6 | 18.7 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 3626.0 | 46.0 | **2.46×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 8735.4 | 32.5 | 1.74× |
+| | **`convert_to_lance_video`** | **487.4** | 45.6 | **2.44×** |
+| **Koch lego** (480×640, 2-cam) | upstream parquet+mp4 | 2014.1 | 26.6 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 8541.0 | 70.8 | **2.66×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 17 335.3 | 49.0 | 1.84× |
+| | **`convert_to_lance_video`** | **2015.9** | 53.8 | **2.02×** |
+
+Reproducible via [`examples/benchmark_formats.py`](examples/benchmark_formats.py).
+
+## Training parity
+
+`convert_to_lance_video` trains a `DiffusionPolicy` on pusht to **68.4 % gym-pusht success** (seed=42, 500 rollouts) — matches the head-to-head upstream parquet+mp4 result (68.0 %) and the published [`lerobot/diffusion_pusht`](https://huggingface.co/lerobot/diffusion_pusht) (65.4 %).
+
+Full numbers (pusht env-eval + ALOHA cups_open held-out MSE across all storage modes) in [`docs/benchmarks.md`](https://lancedb.github.io/lerobot-lancedb/benchmarks/). Reproducers: [`examples/train_and_eval_lance.py`](examples/train_and_eval_lance.py) and [`examples/aloha_loader_parity.py`](examples/aloha_loader_parity.py).
+
+## Cloud / Hub
+
+Both readers accept `s3://`, `gs://`, `hf://datasets/...`, `hf://buckets/...` URIs and pick up credentials from the usual env vars (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS`, `HF_TOKEN`). Lance does byte-range fetches — no full-dataset download.
+
+Pre-converted reference datasets you can paste directly:
+
+```python
+from lerobot_lancedb import LeRobotLanceDataset, LeRobotLanceVideoDataset
+
+LeRobotLanceDataset(repo_id="lance-format/pusht-lerobot-lancedb")        # 60 MB JPEG layout
+LeRobotLanceVideoDataset(repo_id="lance-format/pusht-lerobot-lancedb-video")  # 8 MB video-blob layout
+```
+
+
+## License
+
+Apache 2.0.

lerobot_lancedb-0.1.0/README.md

@@ -0,0 +1,85 @@
+# lerobot-lancedb
+
+📖 **Docs: <https://lancedb.github.io/lerobot-lancedb/>**
+
+Lance-backed datasets for [LeRobot](https://github.com/huggingface/lerobot). Drop-in replacement for `LeRobotDataset` with two storage layouts:
+
+- **`LeRobotLanceDataset`** — per-frame JPEG bytes (lossy, fastest at single-frame access, optional GPU NVJPEG decode).
+- **`LeRobotLanceVideoDataset`** — per-file mp4 bytes stored via Lance blob v2, decoded on the fly with torchcodec. Bit-exact pixels, ~same disk size as upstream.
+
+Both subclass `LeRobotDataset` so existing trainers / samplers / `isinstance` checks accept them transparently.
+
+## Install
+
+```bash
+pip install lerobot-lancedb
+```
+
+For local development:
+
+```bash
+git clone https://github.com/lancedb/lerobot-lancedb.git
+cd lerobot-lancedb
+pip install -e '.[dev]'
+```
+
+## Quickstart
+
+```bash
+# Convert (recommended path for dtype=video sources)
+lerobot-convert-to-lance-video \
+    --repo-id=lerobot/aloha_static_cups_open \
+    --output=./aloha_cups_open_lance_video --overwrite
+```
+
+```python
+from lerobot_lancedb import LeRobotLanceVideoDataset
+ds = LeRobotLanceVideoDataset(root="./aloha_cups_open_lance_video")
+```
+
+For the JPEG layout, use `lerobot-convert-to-lance` and `LeRobotLanceDataset` instead. See the [docs](https://lancedb.github.io/lerobot-lancedb/) for the full CLI / API reference.
+
+## Benchmark
+
+Realistic training read pattern (`delta_timestamps`, 8 frames / sample, batch 32, num_workers 4, CPU decode, H100):
+
+| dataset | format | size MB | delta_ts fps | **speedup** |
+|---|---|---:|---:|---:|
+| **pusht** (96×96, 1-cam) | upstream parquet+mp4 | 7.3 | 750 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 60.0 | 3510 | **4.68×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 105.6 | 2909 | 3.88× |
+| | **`convert_to_lance_video`** | **8.0** | 2853 | **3.80×** |
+| **ALOHA cups_open** (480×640, 4-cam) | upstream parquet+mp4 | 485.6 | 18.7 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 3626.0 | 46.0 | **2.46×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 8735.4 | 32.5 | 1.74× |
+| | **`convert_to_lance_video`** | **487.4** | 45.6 | **2.44×** |
+| **Koch lego** (480×640, 2-cam) | upstream parquet+mp4 | 2014.1 | 26.6 | 1.00× |
+| | `convert_to_lance` (JPEG-95) | 8541.0 | 70.8 | **2.66×** |
+| | `convert_to_lance --jpeg-quality=100 --jpeg-subsampling=0` | 17 335.3 | 49.0 | 1.84× |
+| | **`convert_to_lance_video`** | **2015.9** | 53.8 | **2.02×** |
+
+Reproducible via [`examples/benchmark_formats.py`](examples/benchmark_formats.py).
+
+## Training parity
+
+`convert_to_lance_video` trains a `DiffusionPolicy` on pusht to **68.4 % gym-pusht success** (seed=42, 500 rollouts) — matches the head-to-head upstream parquet+mp4 result (68.0 %) and the published [`lerobot/diffusion_pusht`](https://huggingface.co/lerobot/diffusion_pusht) (65.4 %).
+
+Full numbers (pusht env-eval + ALOHA cups_open held-out MSE across all storage modes) in [`docs/benchmarks.md`](https://lancedb.github.io/lerobot-lancedb/benchmarks/). Reproducers: [`examples/train_and_eval_lance.py`](examples/train_and_eval_lance.py) and [`examples/aloha_loader_parity.py`](examples/aloha_loader_parity.py).
+
+## Cloud / Hub
+
+Both readers accept `s3://`, `gs://`, `hf://datasets/...`, `hf://buckets/...` URIs and pick up credentials from the usual env vars (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS`, `HF_TOKEN`). Lance does byte-range fetches — no full-dataset download.
+
+Pre-converted reference datasets you can paste directly:
+
+```python
+from lerobot_lancedb import LeRobotLanceDataset, LeRobotLanceVideoDataset
+
+LeRobotLanceDataset(repo_id="lance-format/pusht-lerobot-lancedb")        # 60 MB JPEG layout
+LeRobotLanceVideoDataset(repo_id="lance-format/pusht-lerobot-lancedb-video")  # 8 MB video-blob layout
+```
+
+
+## License
+
+Apache 2.0.

lerobot_lancedb-0.1.0/pyproject.toml

@@ -0,0 +1,86 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "lerobot-lancedb"
+version = "0.1.0"
+description = "Lance-backed datasets for LeRobot — frame-level random access on local disk and cloud (S3 / GCS / HF Hub / HF Buckets)."
+readme = "README.md"
+license = { text = "Apache-2.0" }
+requires-python = ">=3.12"
+authors = [
+    { name = "Ayush Chaurasia", email = "ayush@lancedb.com" },
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+keywords = ["lerobot", "lancedb", "lance", "robotics", "datasets", "dataloader"]
+
+dependencies = [
+    # We subclass lerobot.datasets.LeRobotDataset so isinstance checks pass
+    # for downstream training code (factories, samplers, etc.). We don't
+    # depend on the [dataset] extra explicitly because older lerobot versions
+    # bundled those deps into the base install. Users on lerobot>=0.6 should
+    # install with `lerobot-lancedb` + `lerobot[dataset]` together.
+    "lerobot>=0.5.0",
+    "datasets>=4.0.0,<5.0.0",
+    "pyarrow>=21.0.0,<30.0.0",
+    "lancedb>=0.20.0,<1.0.0",
+    "pylance>=0.20.0,<1.0.0",
+    "numpy>=2.0.0,<2.3.0",
+    "Pillow>=10.0.0",
+    "torch>=2.7,<2.11.0",
+    "torchvision>=0.22.0",
+]
+
+[project.optional-dependencies]
+test = [
+    "pytest>=8.1.0,<9.0.0",
+    "pytest-timeout>=2.4.0,<3.0.0",
+]
+dev = [
+    "lerobot-lancedb[test,docs]",
+    "ruff>=0.14.1",
+    "build>=1.2",
+    "twine>=5.1",
+]
+docs = [
+    "mkdocs>=1.6",
+    "mkdocs-material>=9.5",
+    "pymdown-extensions>=10.0",
+]
+
+[project.scripts]
+lerobot-convert-to-lance = "lerobot_lancedb.scripts.convert_to_lance:main"
+lerobot-convert-to-lance-video = "lerobot_lancedb.scripts.convert_to_lance_video:main"
+
+[project.urls]
+homepage = "https://github.com/lancedb/lerobot-lancedb"
+issues = "https://github.com/lancedb/lerobot-lancedb/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.ruff]
+target-version = "py312"
+line-length = 110
+
+[tool.ruff.lint]
+select = ["E", "W", "F", "I", "UP", "B", "PLC0415"]
+ignore = ["E501"]
+
+[tool.ruff.lint.per-file-ignores]
+# Tests legitimately gate imports behind ``pytest.importorskip`` for optional
+# extras, so allowing local imports inside test functions is intentional.
+"tests/*.py" = ["PLC0415"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra"

lerobot_lancedb-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

lerobot_lancedb-0.1.0/src/lerobot_lancedb/__init__.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+
+# Copyright 2025 lerobot-lancedb contributors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+"""Lance-backed datasets for LeRobot."""
+
+from __future__ import annotations
+
+from .auto import make_lerobot_dataset
+from .benchmark import benchmark_throughput, print_throughput_table
+from .dataset import LeRobotLanceDataset
+from .lance_video_dataset import LeRobotLanceVideoDataset
+from .writer import convert_to_lance, convert_to_lance_video
+
+__version__ = "0.1.0.dev0"
+
+
+__all__ = [
+    "LeRobotLanceDataset",
+    "LeRobotLanceVideoDataset",
+    "benchmark_throughput",
+    "convert_to_lance",
+    "convert_to_lance_video",
+    "make_lerobot_dataset",
+    "print_throughput_table",
+    "__version__",
+]

lerobot_lancedb-0.1.0/src/lerobot_lancedb/_spawn_compat.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+
+# Copyright 2025 lerobot-lancedb contributors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+"""Multiprocessing-mode helpers used by the Lance backend.
+
+LanceDB maintains an internal tokio runtime in the parent process. The runtime
+does not survive ``fork()`` cleanly: a worker spawned via fork can hit a torn
+heap inherited from a parent thread that was mid-allocation, producing glibc
+heap-corruption crashes (``malloc(): invalid size``, ``free(): invalid
+pointer``). The crashes are deterministic on cloud reads (S3, HF Buckets) at
+``num_workers >= 8`` and flaky at lower counts. Forcing ``spawn`` on Linux
+avoids the issue at the cost of ~7s extra import time per worker, paid once.
+"""
+
+from __future__ import annotations
+
+import logging
+import multiprocessing as mp
+import sys
+
+_SPAWN_FORCED = False
+
+
+def force_spawn_for_lance() -> None:
+    """Idempotently switch multiprocessing to ``spawn`` on Linux.
+
+    Called from :class:`LeRobotLanceDataset.__init__`. No-op when:
+
+    * Running on macOS (already defaults to spawn).
+    * The current process has already chosen a non-fork start method.
+    """
+    global _SPAWN_FORCED
+    if _SPAWN_FORCED:
+        return
+    _SPAWN_FORCED = True
+
+    if sys.platform != "linux":
+        return
+
+    current = mp.get_start_method(allow_none=True)
+    if current not in (None, "fork"):
+        return
+
+    try:
+        mp.set_start_method("spawn", force=True)
+        logging.info(
+            "lerobot-lancedb: multiprocessing start method set to 'spawn' "
+            "(was %s) — workaround for lancedb fork-unsafety.",
+            current or "default (fork)",
+        )
+    except RuntimeError as exc:
+        logging.warning(
+            "lerobot-lancedb could not switch multiprocessing to 'spawn' "
+            "(%s); DataLoader workers may crash.",
+            exc,
+        )
+
+    try:
+        import torch  # noqa: PLC0415  — optional: tolerate torch missing at install time
+
+        torch.multiprocessing.set_sharing_strategy("file_system")
+    except (ImportError, RuntimeError) as exc:
+        logging.warning(
+            "lerobot-lancedb could not switch torch sharing strategy to "
+            "'file_system' (%s); workers may misbehave on /dev/shm IPC.",
+            exc,
+        )
+
+
+__all__ = ["force_spawn_for_lance"]