Files

T

SolitaryThinker c426847cb6 [bugfix]: FastWan-QAD weights moved to transformer/ on HF — try both paths

The pinned generator_inference_transformer/ path now 404s; the repo
ships transformer/diffusion_pytorch_model.safetensors. Found during
the GB200 FLASHINFER_SAGE_ATTN3 shape-collection run.

2026-07-09 13:17:18 -07:00

attention_example.py

Fix LoRA load from training checkpoint (#719 )

2025-08-09 20:46:00 -05:00

FastWan_QAD_TAEHV.py

[bugfix]: FastWan-QAD weights moved to transformer/ on HF — try both paths

2026-07-09 13:17:18 -07:00

fp4_attn_wan2_1_1_3b.py

[Bugfix] FP4 FA4 installation fix (#1367 )

2026-05-19 22:45:24 -07:00

fp8_wan2_1_1_3b.py

[feat] QAD 5090: FP8 linear layer inference (#1465 )

2026-06-22 18:25:06 -07:00

nvfp4_qat_wan2_1_1_3b.py

[docs] QAD 5090: Add NVFP4 + Attn-QAT inference example and how-to (9/12) (#1458 )

2026-06-16 14:36:50 -07:00

README.md

[Misc] Remove Teacache (#1121 )

2026-02-22 16:53:07 -08:00

text_encoder_quant_example.py

[feat] Support text encoder weight override and quantization (#983 )

2026-01-03 15:33:33 -06:00

torch_compile_example.py

[docs] Document enable_torch_compile (+ A/B example) (#1366 )

2026-05-22 00:25:42 -07:00

README.md

Optimization Examples

python examples/inference/optimizations/attention_example.py