admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-23 09:46:00 +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"]