ViperEkura 32fd03a025 feat: add CudaBackend and rename to fwd_decode/fwd_prefill ...

- CudaBackend: paged decode via attn_paged_decode, prefill via attn_prefill
- Decode uses req_to_token as page_table with page_size=1
- Falls back to TorchNativeBackend when kernel unavailable
- Rename forward_decode/forward_extend to fwd_decode/fwd_prefill
- Register ATTN_BACKEND.CUDA in _BACKEND_REGISTRY

2026-07-30 18:45:33 +08:00

..

__init__.py

feat: add CudaBackend and rename to fwd_decode/fwd_prefill

2026-07-30 18:45:33 +08:00

attention_backend.py

feat: add CudaBackend and rename to fwd_decode/fwd_prefill

2026-07-30 18:45:33 +08:00

attention_ops.py

refactor: unify extension API to blhd layout and is_causal

2026-07-30 18:39:20 +08:00

loader.py

feat: wire up paged decode CUDA kernel to Python extension

2026-07-11 18:40:49 +08:00