llama.cpp
a66d5058 - graph: guard iswa kq_mask on its own buffer (#24294)

Commit
37 days ago
graph: guard iswa kq_mask on its own buffer (#24294) A SWA-only draft head (e.g. StepFun MTP) leaves the base sub-cache empty, so its kq_mask buffer stays null and asserts at load. Guard each mask on its own buffer in set_input and can_reuse, base and swa. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Parents
Loading