admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-06-18 16:57:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

build(deps): pin datasets to the datasets#8259 merge commit

Browse Source 
The native streaming pipeline calls .shuffle() on top of batch(by_column=...),
which crashes on released datasets 5.0.0 (batch-accumulator flag dropped on
shard/shuffle re-creation). The fix (datasets#8259) is merged but unreleased,
so pin datasets to the merge commit 2c45eab on this branch via [tool.uv.sources].
Drop this pin and bump the floor in `dependencies` once the next datasets
release ships the fix.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-06-11 18:28:41 +02:00
parent 4e056081cb
commit 984b400e5c
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pyproject.toml
+4
View File
@@ -333,6 +333,10 @@ explicit = true
[tool.uv.sources]
torch = [{ index = "pytorch-cu128", marker = "sys_platform == 'linux'" }]
torchvision = [{ index = "pytorch-cu128", marker = "sys_platform == 'linux'" }]
# Temporary: the native streaming pipeline needs batch(by_column=...) to survive shard/shuffle
# re-creation, fixed in datasets#8259 (merged, not yet released). Pin to the merge commit until the
# next datasets release ships it, then drop this and bump the floor in `dependencies`.
datasets = { git = "https://github.com/huggingface/datasets.git", rev = "2c45eab1bb975ac3d846f2aa6217b82adec8eba3" }
[tool.setuptools.package-data]
lerobot = ["envs/*.json"]
uv.lock
Generated
+3 -7
View File
@@ -1084,8 +1084,8 @@ wheels = [
[[package]]
name = "datasets"
version = "5.0.0"
source = { registry = "https://pypi.org/simple" }
version = "5.0.1.dev0"
source = { git = "https://github.com/huggingface/datasets.git?rev=2c45eab1bb975ac3d846f2aa6217b82adec8eba3#2c45eab1bb975ac3d846f2aa6217b82adec8eba3" }
dependencies = [
{ name = "dill" },
{ name = "filelock" },
@@ -1102,10 +1102,6 @@ dependencies = [
{ name = "tqdm" },
{ name = "xxhash" },
]
sdist = { url = "https://files.pythonhosted.org/packages/d9/85/ce4f780c32f7e36d71257f1c27e8ba898ebe379cb54f211f5f2013f2c219/datasets-5.0.0.tar.gz", hash = "sha256:83dbbbdb07a33b82192b8c419deb18739b138ee2ce1a322d55ce6b100954ec1a", size = 631708, upload-time = "2026-06-05T13:18:26.124Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/05/66/73034ad30b59f13439b75e620989dacba4c047256e358ba7c2e9ec98ea22/datasets-5.0.0-py3-none-any.whl", hash = "sha256:7dd34927a0fd7046e98aad5cb9430e699c373238a15befa7b9bf22b991a7fee6", size = 555084, upload-time = "2026-06-05T13:18:24.435Z" },
]
[[package]]
name = "debugpy"
@@ -3078,7 +3074,7 @@ requires-dist = [
{ name = "av", marker = "extra == 'av-dep'", specifier = ">=15.0.0,<16.0.0" },
{ name = "cmake", specifier = ">=3.29.0.1,<4.2.0" },
{ name = "contourpy", marker = "extra == 'matplotlib-dep'", specifier = ">=1.3.0,<2.0.0" },
{ name = "datasets", marker = "extra == 'dataset'", specifier = ">=4.7.0,<6.0.0" },
{ name = "datasets", marker = "extra == 'dataset'", git = "https://github.com/huggingface/datasets.git?rev=2c45eab1bb975ac3d846f2aa6217b82adec8eba3" },
{ name = "debugpy", marker = "extra == 'dev'", specifier = ">=1.8.1,<1.9.0" },
{ name = "decord", marker = "(platform_machine == 'AMD64' and extra == 'groot') or (platform_machine == 'x86_64' and extra == 'groot')", specifier = ">=0.6.0,<1.0.0" },
{ name = "deepdiff", marker = "extra == 'deepdiff-dep'", specifier = ">=7.0.1,<9.0.0" },