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 7f2cbd9a4d
CANN: handle in-place ROPE on non-contiguous f32 tensors (#20274) 
RotaryPositionEmbedding on CANN fails when src and dst share the same
non-contiguous buffer (inplace + view), because the operator overwrites
source data before it is fully read.

Add a branch that detects this case and uses contiguous temporary
buffers: copy src to temp, run ROPE into another temp, then copy back
to the non-contiguous dst. Fixes 20 failing ROPE tests (f32, v=1,
inplace=1).

Signed-off-by: noemotiovon <757486878@qq.com>
 		2026-03-19 14:05:01 +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: handle in-place ROPE on non-contiguous f32 tensors (#20274) 2026-03-19 14:05:01 +08:00
aclnn_ops.h docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
common.h docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
ggml-cann.cpp CANN: support flash attention for head dim not multiple of 16, fix ALiBi slope offset (#20031) 2026-03-19 11:02:42 +08:00