Chenguang Li 54f5c02f29 CANN: add RoPE cache preload before ACL graph capture (llama/20747) ...

ACL graph capture disallows host-to-device memcpy and device memory
malloc/free on the captured stream. Pre-load the RoPE cache before
capture so that:
- Host-to-device copies and allocations run on the non-captured stream
- Cache metadata is populated and memory pool is warmed up
- During capture, only on-device computations are recorded; host-side
  and allocation branches are skipped

2026-03-29 15:04:36 +03:00

..

cmake

cmake : remove unused file (ggml/1419)

2026-02-08 09:29:10 +02:00

include

ggml : restore ggml_type_sizef() to aboid major version bump (ggml/1441)

2026-03-18 15:18:24 +02:00

src

CANN: add RoPE cache preload before ACL graph capture (llama/20747)

2026-03-29 15:04:36 +03:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.9.8 (ggml/1442)

2026-03-18 15:18:24 +02:00