ViperEkura 3406157431 refactor: standardize packed 3d inference ...

- keep training attention on dense 4d tensors
- use packed 3d tensors with KV cache for inference
- extend CUDA rotary embedding to packed 3d inputs
- adapt torch, CUDA and FlashAttention backend dispatch

2026-08-16 13:24:02 +08:00

..

test_encoder.py

refactor: simplify BaseFactory and separate ModelFactory from AutoModel

2026-07-30 09:38:20 +08:00

test_forward_configs.py

refactor: stateless MoE routing with grouped dispatch

2026-08-05 18:42:12 +08:00

test_lora.py

test: prune low-value and duplicate tests

2026-08-01 16:01:20 +08:00

test_model_forward.py

refactor: standardize packed 3d inference

2026-08-16 13:24:02 +08:00

test_tie_weight.py

refactor: remove H5 storage backend in favor of mmap bin

2026-07-29 12:50:27 +08:00