ViperEkura 0e7fe57d96 fix: use max_context_len for stable num_splits in paged decode ...

- PagedKV::host_kv_len now returns max_context_len instead of max_seq_len
- Eliminates grid-z instability for CUDA graph capture/replay
- Restore skip_no_kernel re-export accidentally removed by ruff --fix

2026-08-07 14:42:53 +08:00

..

conftest.py

fix: use max_context_len for stable num_splits in paged decode

2026-08-07 14:42:53 +08:00

test_backend_equivalence.py

style: fix ruff lint warnings

2026-08-07 14:17:48 +08:00

test_backend.py

style: fix ruff lint warnings

2026-08-07 14:17:48 +08:00

test_kernel_mask.py

fix: broadcast ref/old model state_dict for FSDP

2026-07-31 08:32:22 +08:00