ViperEkura d565d44c43 fix: harden attention kernel boundaries ...

- fix scalar prefill head_dim=32 out-of-bounds via G=4 dispatch
- fix MMA decode 4D mask head indexing and invalid-row mask access
- add q_head/kv_head divisibility and head-dim contiguity checks
- validate split-KV scratch and decode out_buf layout in bindings
- set max dynamic shared memory for scalar decode D=256
- cover scalar prefill D=32 in pure C test

2026-08-09 14:53:24 +08:00

..

attn_paged_test.cu

refactor: use C++17 struct dispatch in csrc tests, tighten paged tolerances to 0.01

2026-08-09 10:23:12 +08:00

attn_test.cu

fix: harden attention kernel boundaries

2026-08-09 14:53:24 +08:00

test_utils.cuh

refactor: unify paged and contiguous attention kernels via KVSource policy

2026-08-05 14:06:13 +08:00