Article URL: https://github.com/Robbyant/lingbot-map Comments URL: https://news.ycombinator.com/item?id=48941908 Points: 9 # Comments: 0

PyTorch 2.8.0 is the recommended version because NVIDIA Kaolin (required by the batch rendering pipeline) has prebuilt wheels for torch-2.8.0_cu128. If you only need demo.py you may use a newer PyTorch, but the batch renderer then requires building Kaolin from source. For other CUDA versions, see PyTorch Get Started. FlashInfer provides paged KV cache attention for efficient streaming inference. It is a pure-Python package that JIT-compiles CUDA kernels on first use, so a single wheel works across CUDA/PyTorch versions: --index-url https://pypi.org/simple is only needed if your default pip index is an internal mirror that doesn't have flashinfer-python. (Optional) For faster first-use, you can additionally install a CUDA-specific JIT cache: pip install flashinfer-jit-cache -f https://flashinfer.ai/whl/cu128/flashinfer-jit-cache/. See FlashInfer installation for details. If FlashInfer is not installed, the model falls back to SDPA (PyTorch native attention) via --use_sdpa. 🚧 Coming soon: we're training an stronger model that supports longer sequences — stay tuned. This launches an interactive viser viewer at http://localhost:8080. See Interactive Demo below for the full set of scenes and flags, or jump to Offline Rendering Pipeline for long-sequence batch rendering. Run demo.py for interactive 3D visualization via a browser-based viser viewer (default http://localhost:8080). Sequence is too long for the interactive viser viewer — this clip was rendered with the Offline Rendering Pipeline. See that section for the full command. Use --keyframe_interval to reduce KV cache memory by only keeping every N-th frame as a keyframe. Non-keyframe frames still produce predictions but are not stored in the cache. This is useful for long sequences which exceed 320 frames (We train with video RoPE on 320 views, so performance degrades when the KV cache stores more than 320 views. Using a keyframe strategy allows inference over longer sequences.).