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

..

config

feat: add field and model validators to config classes

2026-07-30 08:41:14 +08:00

dataset

refactor: remove H5 storage backend in favor of mmap bin

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

extension

feat: add CudaBackend and rename to fwd_decode/fwd_prefill

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

inference

refactor: use single-index access and update docs for cache architecture

2026-07-30 17:47:04 +08:00

model

refactor: use single-index access and update docs for cache architecture

2026-07-30 17:47:04 +08:00

parallel

refactor: inline parallel utils into executor module

2026-07-30 07:54:54 +08:00

preprocessing

refactor: remove H5 storage backend in favor of mmap bin

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

serialization

refactor: remove H5 storage backend in favor of mmap bin

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

tokenize

refactor: simplify BaseFactory and separate ModelFactory from AutoModel

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

trainer

refactor: simplify BaseFactory and separate ModelFactory from AutoModel

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

__init__.py

refactor: remove H5 storage backend in favor of mmap bin

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

factory.py

refactor: simplify BaseFactory and separate ModelFactory from AutoModel

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

protocols.py

refactor: 重构训练后端为 Executor 模式

2026-05-24 20:35:44 +08:00

signal_handler.py

refactor: move signal_handler from parallel/ to top-level for broader reuse

2026-07-28 10:36:17 +08:00