Skip to content

[fix] Fix latent handoff and FastWan-QAD example path#1557

Open
aryan5v wants to merge 4 commits into
hao-ai-lab:mainfrom
aryan5v:fix-latent-handoff-fastwan-qad-path
Open

[fix] Fix latent handoff and FastWan-QAD example path#1557
aryan5v wants to merge 4 commits into
hao-ai-lab:mainfrom
aryan5v:fix-latent-handoff-fastwan-qad-path

Conversation

@aryan5v

@aryan5v aryan5v commented Jul 5, 2026

Copy link
Copy Markdown
Contributor

Summary

  • return latent worker outputs on CPU before sending them to the parent process, avoiding CUDA IPC for external decode paths
  • point the FastWan-QAD TAEHV example at the published FastVideo/FastWan-QAD-1.3B pipeline and existing transformer checkpoint path

Testing

  • python3 -m py_compile fastvideo/tests/worker/test_multiproc_executor.py fastvideo/worker/multiproc_executor.py examples/inference/optimizations/FastWan_QAD_TAEHV.py

Closes #1524

@aryan5v

aryan5v commented Jul 5, 2026

Copy link
Copy Markdown
Contributor Author

Rebased onto latest main, dropped the superseded fastvideo/platforms/cuda.py SM120 fallback, and pushed the cleaned branch under fix-latent-handoff-fastwan-qad-path.

The PR now keeps only the two still-needed fixes:

  • CPU handoff for latent worker outputs before returning to the parent process
  • FastWan-QAD TAEHV example defaults/path fix

Validation: python3 -m py_compile fastvideo/tests/worker/test_multiproc_executor.py fastvideo/worker/multiproc_executor.py examples/inference/optimizations/FastWan_QAD_TAEHV.py.

@mergify mergify Bot added type: bugfix Bug fix scope: inference Inference pipeline, serving, CLI scope: infra CI, tests, Docker, build labels Jul 5, 2026
@mergify

mergify Bot commented Jul 5, 2026

Copy link
Copy Markdown
Contributor

Merge Protections

🔴 1 of 1 protections blocking · waiting on 👀 reviews and 🤖 CI

Protection Waiting on
🔴 PR merge requirements 👀 reviews and 🤖 CI

🔴 PR merge requirements

Waiting for

  • #approved-reviews-by>=1
  • check-success=fastcheck-passed
  • check-success=full-suite-passed
This rule is failing.
  • #approved-reviews-by>=1
  • check-success=fastcheck-passed
  • check-success=full-suite-passed
  • check-success~=pre-commit
  • title~=(?i)^\[(feat|feature|bugfix|fix|refactor|perf|ci|doc|docs|misc|chore|kernel|new.?model|skill|skills|infra)\]

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the FastWan_QAD_TAEHV.py example script with correct usage instructions and updated model defaults. It also introduces a helper function _prepare_worker_output_for_parent in multiproc_executor.py to move latent CUDA tensors to the CPU before sending them to the parent process, avoiding CUDA IPC issues for small latent outputs, and adds corresponding unit tests. The reviewer suggested improving the robustness of this helper function by handling cases where fastvideo_args might be None or lack the output_type attribute.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

Comment thread fastvideo/worker/multiproc_executor.py Outdated
@aryan5v aryan5v marked this pull request as ready for review July 6, 2026 18:15
@mergify

mergify Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Pre-commit checks failed

Hi @aryan5v, the pre-commit checks have failed. To fix them locally:

# Install pre-commit if you haven't already
uv pip install pre-commit
pre-commit install

# Run all checks and auto-fix what's possible
pre-commit run --all-files

Common fixes:

  • yapf: yapf -i <file> (formatting)
  • ruff: ruff check --fix <file> (linting)
  • codespell: codespell --write-changes <file> (spelling)

After fixing, commit and push the changes. The checks will re-run automatically.

For future commits, pre-commit will run automatically on changed files before each commit.

aryan5v and others added 3 commits July 6, 2026 21:40
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
@aryan5v aryan5v force-pushed the fix-latent-handoff-fastwan-qad-path branch from bde00ce to ab19210 Compare July 7, 2026 04:45
@mergify

mergify Bot commented Jul 7, 2026

Copy link
Copy Markdown
Contributor

This PR has merge conflicts with the base branch. Please rebase:

git fetch origin main
git rebase origin/main
# Resolve any conflicts, then:
git push --force-with-lease

@mergify mergify Bot added the needs-rebase PR has merge conflicts label Jul 7, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

needs-rebase PR has merge conflicts scope: inference Inference pipeline, serving, CLI scope: infra CI, tests, Docker, build type: bugfix Bug fix

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug] FastWan-QAD FP4 fails on RTX 5080 SM120 during FlashInfer CUTLASS runtime compilation

1 participant