models ¶

Modules¶

fastvideo.tests.train.models.test_load_hunyuan ¶

GPU loading + forward smoke test for HunyuanModel.

Loads the real HunyuanVideo checkpoint (~13B at bf16) via HunyuanModel.__init__ and runs one transformer forward pass on synthetic inputs. Hunyuan's transformer takes a slightly different forward signature than Wan (no encoder_attention_mask, no return_dict); this test mirrors the kwargs in HunyuanModel._build_distill_input_kwargs.

Classes¶

Functions¶

fastvideo.tests.train.models.test_load_wan ¶

GPU loading + forward smoke test for WanModel.

Loads the real Wan2.1 1.3B checkpoint via WanModel.__init__ and runs one transformer forward pass on synthetic inputs. Catches loader or forward-signature regressions in fastvideo.train.models.wan.WanModel and the underlying WanTransformer3DModel.

Classes¶

Functions¶

fastvideo.tests.train.models.test_load_wan_causal ¶

GPU loading smoke test for WanCausalModel.

Verifies that WanCausalModel.__init__ resolves the CausalWanTransformer3DModel class override and successfully loads weights from the regular Wan2.1 1.3B checkpoint.

A real forward pass is intentionally omitted here: the causal transformer requires per-frame timesteps, a block-causal attention mask, and KV cache state that WanCausalModel.predict_noise_streaming manages for production callers. PR 5 (per-method tests) exercises that streaming forward path end-to-end.