Skip to content

build: optimize native and tilelang incremental builds. - #2068

Open
jarvis666666 wants to merge 3 commits into
xLLM-AI:mainfrom
jarvis666666:main
Open

build: optimize native and tilelang incremental builds.#2068
jarvis666666 wants to merge 3 commits into
xLLM-AI:mainfrom
jarvis666666:main

Conversation

@jarvis666666

@jarvis666666 jarvis666666 commented Jul 29, 2026

Copy link
Copy Markdown

Description

  • derive build parallelism from the available physical CPU topology.
  • reuse persistent Cargo and TileLang artifacts across build directories.
  • eliminate duplicate source compilation and stabilize CMake compiler flags.
  • skip redundant CMake configuration when command and environment inputs are unchanged.
  • add focused tests for CPU topology, cache paths, and CMake configure reuse.

Related Issues

Change Type

  • Bug fix
  • New feature
  • Performance improvement
  • Refactor
  • Documentation
  • Test
  • Build or CI

Pull Request Checklist

Thank you for contributing to xLLM. Before requesting review, please make sure the following items are complete.

PR Title and Commit Messages

  • The PR title and each commit message follow the xLLM commit format: <type>: <subject>.

Allowed types: feat, bugfix, docs, test, refactor, chore, style, revert, perf, model, build, release.
The subject should use clear English, start with a verb, include at least 4 words, and end with ..

Pre-commit Checks

  • I have installed pre-commit by running pip install pre-commit or an equivalent command.
  • I have installed the hooks with pre-commit install.
  • I have run pre-commit run --all-files and fixed any reported issues.

If you are unsure how to set up pre-commit, see the pre-commit documentation.

Self Review

  • I have self-reviewed the code according to .agents/skills/code-review/references/custom-code-style.md, especially code written or assisted by AI.
  • I have rebased this PR onto the latest main branch.

Build and Test Coverage

  • Tests have been added or updated as needed.
  • CUDA: python setup.py build test has passed on a CUDA machine.
  • NPU: python setup.py build test has passed on an NPU machine.
  • MLU: python setup.py build test has passed on an MLU machine.

Reviewer Notes

jarvis666666 and others added 2 commits July 29, 2026 10:14
- derive build parallelism from the available physical CPU topology.
- reuse persistent Cargo and TileLang artifacts across build directories.
- eliminate duplicate source compilation and stabilize CMake compiler flags.
- skip redundant CMake configuration when command and environment inputs are unchanged.
- add focused tests for CPU topology, cache paths, and CMake configure reuse.
@XuZhang99 XuZhang99 changed the title build:optimize native and tilelang incremental builds build:optimize native and tilelang incremental builds. Jul 29, 2026
  - derive compile and archive job limits from CPU topology
  - preserve Cargo caches across CMake clean operations
  - namespace TileLang caches by source and toolchain fingerprints
  - make TileLang manifests portable, atomic, and concurrency-safe
  - add coverage for cache reuse, relocation, and concurrent builds
@XuZhang99 XuZhang99 changed the title build:optimize native and tilelang incremental builds. build: optimize native and tilelang incremental builds. Jul 31, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant