CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

CANN: Optimize RMS_NORM using cache (#15419)

Browse Source 
* [CANN] Optimize RMS_NORM using cache

Signed-off-by: noemotiovon <757486878@qq.com>

* fix typo

Signed-off-by: noemotiovon <757486878@qq.com>

* fix review comment

Signed-off-by: noemotiovon <757486878@qq.com>

* codestyle adjustment

Signed-off-by: noemotiovon <757486878@qq.com>

---------

Signed-off-by: noemotiovon <757486878@qq.com>
This commit is contained in:
Chenguang Li
2025-08-22 14:12:07 +08:00
committed by GitHub
parent 54a241f505
commit a0f98dd604
2 changed files with 121 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cann/common.h
View File

@@ -379,6 +379,10 @@ struct ggml_backend_cann_context {
cann_task_queue task_queue;
bool async_mode;
bool support_set_rows;
void* f32_zero_cache = nullptr;
void* f32_one_cache = nullptr;
int64_t f32_zero_cache_element = 0;
int64_t f32_one_cache_element = 0;
aclrtStream streams[GGML_CANN_MAX_STREAMS] = {nullptr}; /**< Array of streams for the device. */