[v1.6.0] Release Schedule and Tracker
维护者通常 1 天内回复
@JacobSzwejbka 已经在做这个了。
开始于 2026年10月8日。
评估
这个 Issue 还没有评估数据。
描述
🚀 The feature, motivation and pitch
[v1.6.0] Release Schedule and Tracker
The v1.6.0 release will be released from the release/1.6 branch. After branch cut, this branch will accept fixes according to the cherry-pick criteria below.
Release Schedule
- Branch Cut Date: Friday, October 16, 2026
- Release branch finalized, documentation and tutorials finalized: Wednesday, October 21, 2026 (last day; proposed)
- Intended Release Date: Thursday, October 29, 2026
The intended release date follows the PyTorch 2.15 release schedule. If the PyTorch release moves, the ExecuTorch release target will move to the following calendar day.
This issue is for tracking cherry-picks to the release branch.
Cherry-Pick Criteria
Focus on stability and documentation correctness. Ideally only low-risk changes may be cherry-picked from main:
- Critical fixes in core components: build, exir, backends, runtime, sdk
- Bug fixes in demos/examples. No new features or experiments
- Critical bug fixes based on community feedback
- Documentation improvements
- Test/CI fixes
- Release-branch-specific changes (for example, version identifier changes)
Any core component changes or other changes require special dispensation from the release managers. If this applies to your change, write Special Dispensation in the Criteria category and reasons: section of the template below and explain why it should be included.
Cherry-Pick Process
- Ensure your PR has landed in main. This does not apply to release-branch-specific changes.
- Create, but do not land, a PR against the release branch using one of the options below.
- Submit a request in a comment on this issue using the request template below.
Option 1: Use pytorchbot
Use pytorchbot to cherry-pick a PR committed to the main branch. Comment on that PR, selecting the appropriate category:
@pytorchbot cherry-pick --onto release/1.6 -c {regression,critical,fixnewfeature,docs,release,examples,testci}
Command usage
usage: @pytorchbot cherry-pick --onto ONTO [--fixes FIXES] -c
{regression,critical,fixnewfeature,docs,release,examples,testci}
Cherry-pick a pull request onto a release branch for inclusion in a release.
optional arguments:
--onto ONTO Branch to cherry-pick onto (example: release/1.6)
--fixes FIXES Link to the issue fixed by the PR
-c Machine-friendly classification of the cherry-pick reason
Option 2: Manually create a cherry-pick PR
Manual commands
# Find the hash of the commit to cherry-pick.
git log
git fetch origin release/1.6
git checkout -b cherry-pick-for-1.6 origin/release/1.6
git cherry-pick -x <commit>
# Push the branch to your fork and open a PR based against release/1.6,
# either through the GitHub UI or with:
git push <fork-remote> cherry-pick-for-1.6
gh pr create --repo pytorch/executorch --base release/1.6
Cherry-Pick Request Template
Link to landed trunk PR:
*
Link to release branch PR:
*
Criteria category and reasons:
*
Someone from the release team will approve, deny, or request more information. If approved, the release team will merge the PR after tests pass. Do not land the release-branch PR yourself.
If the release team has acted on a cherry-pick request, its comment will be liked. Once the cherry-pick has merged, a rocket reaction will be added to the comment.
Release branch CI: HUD
Version
1.6.0
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
- 主要语言
- Python
- 星标
- 5.1k
- 派生
- 1.2k
- 平均合并
- 2 天 9 小时
- 30 天内合并 PR
- 661
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
pytorch/executorch 的其他 Issue
-
enhancement triaged
难度 2/5 半天 新手友好度 68/100
pytorch/executorch#21640 ·
维护者通常 1 天内回复
-
Prompts of max_seq_len tokens fail to prefill: export_llm bounds the KV-cache token input at max_seq_len - 1 but publishes get_max_seq_len = max_seq_len可能已有人在做 @alpharomercoma 于 1 天前认领。 未关闭
难度 3/5 1-2 天 新手友好度 20/100
pytorch/executorch#23678 ·
维护者通常 1 天内回复
-
QNN sharded LLM export fails: ResolveDebugHandle is not the last edge pass (dep_table entry overwritten by SplitGraph registration)可能已有人在做 @psiddh 于 3 天前认领。 未关闭bug module: llm module: qnn triaged
pytorch/executorch#23580 · 已指派 1 人 ·
维护者通常 1 天内回复
-
难度 4/5 3-5 天 新手友好度 48/100
pytorch/executorch#23553 ·
维护者通常 1 天内回复
-
module: ci module: samsung unstable
难度 2/5 1-3 小时 新手友好度 50/100
pytorch/executorch#23507 · 1 条评论 ·
维护者通常 1 天内回复
查看 pytorch/executorch 的全部 Issue
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 60/100
521xueweihan/HelloGitHub#3924 ·
-
难度 2/5 1-3 小时 新手友好度 67/100
wilbowes/EchoMuse#869 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 85/100
-
namespace operations
难度 1/5 1 小时以内 新手友好度 72/100
EclipseFdn/open-vsx.org#14043 ·
维护者通常 1 天内回复
-
test: TestServeUntilStale races the server's close against the client's sendall (BrokenPipeError under load)可能已有人在做 @evoludigit 今天认领。 未关闭
难度 1/5 1 小时以内 新手友好度 89/100
维护者通常 1 天内回复