Support reasoner video input.#25
Open
foreverlms wants to merge 21 commits into
Open
Conversation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…tion Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…l-exclusion validator Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…pass-throughs Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…te_reasoner_text stub Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ate_reasoner_text Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…nce engine Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…decord/pkl_to_media dep) The repo Qwen3VLProcessor runs do_sample_frames=False and expects a pre-decoded frame list; decode with the inference-canonical torchvision.io.read_video (no undeclared decord dep) and sample toward video_fps via Qwen smart_nframes. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…/plan superseded Always emit reasoner_videos=[video_or_None] (like reasoner_images) so the batch homogeneity check aligns positionally and reliably rejects an image/video/text mix. Add superseded banners to the spec/plan docs (frame-decode + video_fps-only is final). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
foreverlms
force-pushed
the
maoshengl/video_reasoner_inference
branch
from
1b7b175 to
19bd716
Compare
… untracked) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…-commit) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…t for reasoner_videos key - _make_reasoner_sample_args gains video_fps - text-only / with-image get_sample_data tests assert the always-present reasoner_videos:[None] - add test_get_sample_data_reasoner_with_video (monkeypatched decoder) - drop redundant lower-level _get_reasoner_sample_data duplicates (public get_sample_data set covers them) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
1 participant
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.
No description provided.