Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By JiusiServe
Reproduce Long Video Sparse Attention (LVSA) paper headline numbers using bundled benchmarks scripts, including SotA comparison, latency scaling, and scoring with VQeval and VBench-Long, plus figure regeneration.
npx claudepluginhub jiusiserve/longvideosparseattention --plugin lvsa-reproduce-paperShare bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Install LVSA and generate your first long video. Picks SDPA vs FlashInfer, sets the right LVSA_REFERENCE_LATENT_FRAMES per model, verifies the sparse path engaged.
Skills for finding, comparing, running, and prompting AI models on Replicate
Agent-ready playbooks for LLM serving benchmarks, capacity planning, torch-profiler triage, pipeline analysis, compute simulation, SGLang/vLLM SOTA Humanize loops, human code review, production incident triage, and model PR-history dossiers.
Inference-time scaling for LLMs — generate multiple candidates and select the best using voting, scoring, or search
Claude Code skill pack for Runway (18 skills)
Video generation at scale. Generate videos, images, and audio with Runway's API — batch ad campaigns, product videos, multishot stories, and creative iteration. Supports seedance2, gen4.5, veo3, Nano, Banana Pro, and more.
Diagnose LVSA failure modes: silent dense fallback, OOM at long sequences, missing output mp4 in Docker, quality regression at training reference.
Configure and run the LVSA vllm-omni serving plugin: env vars, geometry overrides, hooks for Wan vs HunyuanVideo, multi-GPU Ulysses.
Add LVSA support for a new video diffusion model by implementing the ModelAdapter ABC and wiring it into examples/.
Install LVSA and generate your first long video. Picks SDPA vs FlashInfer, sets the right LVSA_REFERENCE_LATENT_FRAMES per model, verifies the sparse path engaged.
Tune LVSA's sparsity_scale, window_size, n_first_frames, and reference_latent_frames for a target model and quality/speed trade-off.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim