happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src/ggml-cann
History
Chenguang Li 07ff000551
CANN: add RoPE cache preload before ACL graph capture (#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
 		2026-03-23 15:24:06 +08:00
..
CMakeLists.txt CANN: add support for ACL Graph (#15065) 2025-08-06 14:12:42 +08:00
acl_tensor.cpp docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
acl_tensor.h docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
aclnn_ops.cpp CANN: add RoPE cache preload before ACL graph capture (#20747) 2026-03-23 15:24:06 +08:00
aclnn_ops.h CANN: add RoPE cache preload before ACL graph capture (#20747) 2026-03-23 15:24:06 +08:00
common.h CANN: add RoPE cache preload before ACL graph capture (#20747) 2026-03-23 15:24:06 +08:00
ggml-cann.cpp CANN: add RoPE cache preload before ACL graph capture (#20747) 2026-03-23 15:24:06 +08:00