Junda Chen 39a8db2f5d [feat] Reuse Wan inference weights through normal loaders

2026-10-15 11:20:05 -07:00

..

test_fsdp_inference_quantization.py

[feat] add MXFP8 support on H3 (#1796)

2026-09-05 17:08:58 -07:00

test_fsdp_load_releases_checkpoint.py

[new-model] Add native Helios-Distilled T2V pipeline (#1670)

2026-10-07 03:18:24 -07:00

test_inference_weight_cache.py

[feat] Reuse Wan inference weights through normal loaders

2026-10-15 11:20:05 -07:00

test_lora_patch.py

[feat] Add streaming and GPU-accelerated LoRA extraction (#1784)

2026-10-07 04:48:35 -07:00

test_minimax_h3_pdd_loading.py

[feat] FastH3 Ref2VA PDD inference with reference-video VSA sparsity (#1907)

2026-10-02 11:28:07 -07:00

test_text_encoder_unified_memory_offload.py

[perf] Disable every offload path on unified memory, unblocking MiniMax H3 generation on one GB10 (#1715)

2026-08-26 15:32:56 -07:00

test_vae_loading_boundaries.py

[feat] Reuse Wan inference weights through normal loaders

2026-10-15 11:20:05 -07:00

test_wan_family_imports.py

[misc] Remove DreamX World, HunyuanGameCraft, GLM-Image, LongCat, TurboDiffusion, and Z-Image (#1926)

2026-10-14 23:16:32 -07:00

test_weight_broadcast_leader.py

[bugfix] Fix the CUDA device of Ray workers on multi-GPU nodes (#1932)

2026-10-07 15:00:23 -07:00

test_weight_cache.py

[feat] Retain native model weights in a CUDA IPC donor

2026-10-15 01:35:13 -07:00