Cherry-pick latest 4 JianyuLi01 commits from release/v0.17.0rc1 onto release/v0.19.0rc1#2
Merged
Merged
Conversation
Co-authored-by: JianyuLi01 <109940438+JianyuLi01@users.noreply.github.com>
Co-authored-by: JianyuLi01 <109940438+JianyuLi01@users.noreply.github.com>
Co-authored-by: JianyuLi01 <109940438+JianyuLi01@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
JianyuLi01
April 29, 2026 11:15
View session
Copilot AI
added a commit
that referenced
this pull request
Apr 29, 2026
Co-authored-by: JianyuLi01 <109940438+JianyuLi01@users.noreply.github.com>
5 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Ports the 4 most recent commits authored by JianyuLi01 (
jyli@intel.com) onrelease/v0.17.0rc1ontorelease/v0.19.0rc1.Cherry-picks
4c904fcfshrink wan_t2v_size for xpu71fb970atext_to_video.pyandpipeline_wan2_2.pybd6093d8enable profilingdcecdc9arun_t2v.shhunk applied784ccac4fix issue that json not generatedc049edc8restore original images size5cb7fb72Conflict resolutions (minimal)
examples/offline_inference/text_to_video/text_to_video.py— folded v0.17'soutput_type = "latent", theoutput_typesampling param, and the latent-only early-return into the existingprompt_dict/sampling_kwargsform. Did not re-introduceframe_rate=frame_rate(undefined on v0.19).vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py— kept v0.17'sVLLM_OMNI_WAN_PROFILE_TRANSFORMER_ONLYenv-var branch andtorch_dtype=torch.float32VAE load on top of the existing v0.19 code.vllm_omni/diffusion/profiler/torch_profiler.py— accepted the upstream deletion (file was unified intovllm_omni/profiler/omni_torch_profiler.pyby PR [Refactor] Unify torch profiler for omni and diffusion models vllm-project/vllm-omni#2099). Hunks targeting this path in4c904fcf/bd6093d8/784ccac4were therefore dropped;784ccac4reduced to nothing and was skipped.Reviewer note on PR base
The pre-created branch was based on
main, notrelease/v0.19.0rc1. The 3 commits here sit cleanly on top of the current branch tip; if landing onrelease/v0.19.0rc1directly is required, the branch needs to be reset ontorelease/v0.19.0rc1and force-pushed before merge. CodeQL passed; remaining Code Review comments are properties of the upstream commits being ported and were intentionally left as-is per the "minimal change" requirement.