ViperEkura 1b1f1a0707 fix: add dtype guard to FlashAttnBackend capability check ...

- _backend_supports now rejects fp32 for FlashAttnBackend (flash-attn only supports fp16/bf16), preventing runtime crash on fallback chain
- rename test_default_backend_is_torch_native to reflect multi-backend reality
- scheduler test fixture uses bf16 model (matches production, avoids unnecessary 3-step fallback chain)

2026-08-07 23:08:22 +08:00

..

lib

refactor: move compiled kernel .so files into extension/lib

2026-07-31 15:36:32 +08:00

__init__.py

refactor : use factory for attention backends

2026-08-05 15:37:22 +08:00

attention_backend.py

fix: add dtype guard to FlashAttnBackend capability check

2026-08-07 23:08:22 +08:00

attention_ops.py

fix: add out_buf to attn_paged_decode for CUDA graph capture compatibility

2026-08-07 19:45:59 +08:00

loader.py

feat: SGLang-style paged attention kernels replace page-table path

2026-08-01 15:41:25 +08:00

rotary_backend.py

refactor: unify rotary embedding interface and update docs

2026-07-31 16:52:25 +08:00

rotary_ops.py

refactor: unify rotary embedding interface and update docs

2026-07-31 16:52:25 +08:00