3a0f39d626
The public LTX-2 path was previously running full bf16 even when callers set ``pipeline_config.dit_config.quant_config = FP4Config()``, because: * the DiT used plain ``torch.nn.Linear`` for FP4-eligible projections (``attn1/attn2.to_q/k/v/out``, ``audio_to_video_attn``, ``video_to_audio_attn``, FFN ``fc_in``/``fc_out``), so ``LinearBase.quant_method.apply`` was never reached; * the loader did not call ``convert_model_to_fp4`` after weights loaded, so even matched layers had no ``_fp4_weight*`` buffers; * ``QuantizationMethods`` did not register ``"FP4"``, so the typed ``engine.quantization.transformer_quant`` surface had no way to select it. This commit completes the inference wire-up through the existing ``fastvideo.layers.quantization`` registry — no parallel pathway: * swap ``nn.Linear`` → ``ReplicatedLinear`` for the LTX-2 attention ``to_q``/``to_k``/``to_v``/``to_out``/``to_gate_compress`` and the FFN ``fc_in``/``fc_out`` (``GELUApprox.proj`` and ``FeedForward`` ``project_out``). Other linears (timestep MLP, caption proj, patchify, AdaLN scale/shift) stay ``nn.Linear`` to match internal. * port ``_supports_prequantized_input`` and ``_linear_project_with_optional_prequant`` so the attention forward quantizes input once and reuses the ``(x_fp4, x_scale, x_global_sf)`` tuple across q/k/v projections — matches internal exactly. * plumb ``quant_config`` and ``prefix`` through ``BasicAVTransformerBlock`` → ``_init_transformer_blocks`` → ``LTXModel`` → ``LTX2Transformer3DModel`` so each ``ReplicatedLinear`` gets the correct ``ltx2.blocks.<i>.<sub>.<proj>`` prefix that ``FP4Config.get_quant_method`` matches against. * register ``"FP4"`` in ``QuantizationMethods`` literal + ``get_quantization_config`` registry so typed ``engine.quantization.transformer_quant: "FP4"`` resolves to a concrete ``FP4Config()`` instance. * add ``transformer_quant`` carrier on ``FastVideoArgs`` and ``__post_init__._apply_transformer_quant`` to pin the resolved quant config onto ``dit_config.quant_config`` (without overwriting an explicit setter on the dit_config). * add ``_maybe_convert_model_to_fp4`` in ``fsdp_load.py`` that walks the loaded model once and registers ``_fp4_weight*``/``_fp4_alpha``/``_weight_global_sf`` buffers on layers whose ``quant_method`` is ``FP4QuantizeMethod``. flashinfer is imported lazily inside ``convert_model_to_fp4`` so this is a no-op on hosts without the FP4 kernels. * restore ``LinearBase`` fallback to ``UnquantizedLinearMethod`` when ``quant_config.get_quant_method`` returns ``None`` — ``FP4Config`` only tags a curated subset of layers, and the previous ``assert quant_method is not None`` would crash any non-tagged layer that received a quant_config. Non-FP4 callers are unaffected: ``UnquantizedLinearMethod.apply`` runs the standard ``F.linear`` path, and parameter names (``to_q.weight``, ``to_out.0.weight`` from ``nn.ModuleList``) are identical to the previous ``nn.Sequential`` layout. Co-authored-by: Junda (David) Su <90978028+Davids048@users.noreply.github.com> Co-authored-by: Matthew Noto <99706358+RandNMR73@users.noreply.github.com> Co-authored-by: XOR-op <17672363+XOR-op@users.noreply.github.com> Co-authored-by: Zhang Peiyuan <42993249+jzhang38@users.noreply.github.com>
FastVideo Documentation
This directory contains the FastVideo documentation built with MkDocs.
Build the docs locally
# Install dependencies
uv pip install -r requirements-mkdocs.txt
# Serve docs with live reload (recommended for development)
mkdocs serve
# Or build static site
mkdocs build
View the docs
Development server (with live reload)
mkdocs serve
Then open your browser to: http://127.0.0.1:8000
Static build
mkdocs build
python -m http.server -d site/
Then open your browser to: http://localhost:8000
Automatic Deployment
Documentation is automatically built and deployed to GitHub Pages when changes are pushed to the main branch via the .github/workflows/infra-docs.yml workflow.