[None][chore] 2 more WAN multi-gpu tests - #15223
Conversation
|
/bot run |
|
PR_Github #53325 [ run ] triggered by Bot. Commit: |
📝 WalkthroughWalkthroughThis PR adds Flash Attention 4 backend support to multi-GPU visual generation test suites. It detects FA4 and flash_attn_combine kernel availability, then adds new distributed test configurations and correctness checks against HuggingFace references for both T2V pipeline and transformer parallel scenarios. ChangesFA4 Attention Backend Testing Support
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
🧹 Nitpick comments (1)
tests/unittest/_torch/visual_gen/multi_gpu/test_wan_pipeline_parallel.py (1)
341-401: ⚡ Quick winConsider extracting a parameterized worker helper to reduce duplication.
This function shares ~90% of its logic with
_logic_wan_cfg_ulysses_pvae()(lines 275-338). The only differences are the world-size assertion, the args builder called, and the log message. A parameterized helper would reduce maintenance burden if the core workflow changes.However, test clarity often outweighs DRY, so this refactor is optional.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tests/unittest/_torch/visual_gen/multi_gpu/test_wan_pipeline_parallel.py` around lines 341 - 401, The two test functions _logic_wan_cfg2_attn2d2x1_ulysses2_pvae8 and _logic_wan_cfg_ulysses_pvae share almost identical flow; extract a small parameterized worker helper (e.g., _run_wan_pipeline_worker(rank, world_size, checkpoint_path, expected_world_size, args_builder, description)) that performs the world_size assertion, loads the PipelineLoader via the provided args_builder, captures trtllm_video and hf_video, frees resources, does the barrier and rank-0 checks, computes cosine similarity and asserts threshold, and then replace both functions to call this helper with different expected_world_size, args builder functions (_build_cfg2_attn2d2x1_ulysses2_pvae8_args vs the other builder) and a short description string to preserve the unique log message. Ensure the helper uses the same symbols currently referenced: PipelineLoader, _capture_trtllm_video, _capture_hf_video, _free, dist.barrier, DiffusionPipeline.from_pretrained, and _cosine_similarity so behavior remains identical.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@tests/unittest/_torch/visual_gen/multi_gpu/test_wan_pipeline_parallel.py`:
- Around line 341-401: The two test functions
_logic_wan_cfg2_attn2d2x1_ulysses2_pvae8 and _logic_wan_cfg_ulysses_pvae share
almost identical flow; extract a small parameterized worker helper (e.g.,
_run_wan_pipeline_worker(rank, world_size, checkpoint_path, expected_world_size,
args_builder, description)) that performs the world_size assertion, loads the
PipelineLoader via the provided args_builder, captures trtllm_video and
hf_video, frees resources, does the barrier and rank-0 checks, computes cosine
similarity and asserts threshold, and then replace both functions to call this
helper with different expected_world_size, args builder functions
(_build_cfg2_attn2d2x1_ulysses2_pvae8_args vs the other builder) and a short
description string to preserve the unique log message. Ensure the helper uses
the same symbols currently referenced: PipelineLoader, _capture_trtllm_video,
_capture_hf_video, _free, dist.barrier, DiffusionPipeline.from_pretrained, and
_cosine_similarity so behavior remains identical.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 0bff0349-7d9c-4c38-86e7-c588e9bead76
📒 Files selected for processing (2)
tests/unittest/_torch/visual_gen/multi_gpu/test_wan_pipeline_parallel.pytests/unittest/_torch/visual_gen/multi_gpu/test_wan_transformer_parallel.py
|
/bot kill |
|
PR_Github #53358 [ kill ] triggered by Bot. Commit: |
|
PR_Github #53325 [ run ] completed with state |
|
PR_Github #53358 [ kill ] completed with state |
|
/bot run |
|
PR_Github #53364 [ run ] triggered by Bot. Commit: |
|
PR_Github #53364 [ run ] completed with state
|
|
/bot run |
|
PR_Github #53602 [ run ] triggered by Bot. Commit: |
|
PR_Github #53602 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #53614 [ run ] triggered by Bot. Commit: |
|
PR_Github #53614 [ run ] completed with state
|
|
/bot run |
|
PR_Github #53693 [ run ] triggered by Bot. Commit: |
|
PR_Github #53693 [ run ] completed with state
|
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
…2_ring2 waive Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
36b9745 to
9afd049
Compare
|
/bot run |
|
PR_Github #53733 [ run ] triggered by Bot. Commit: |
|
PR_Github #53733 [ run ] completed with state
|
|
/bot run |
|
PR_Github #53900 [ run ] triggered by Bot. Commit: |
|
PR_Github #53900 [ run ] completed with state |
Summary by CodeRabbit
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.