llama.cpp
c18610b4 - CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)

Commit

230 days ago

CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216) * CANN Support Ascend310P to accelerate F32 and F16 Model * Add compile option soc type macro ASCEND_310P to ggml-cann lib * Remove unused code * Remove the ascend soc_type hard code compile option in CMakelist.txt

References

#10216 - CANN Support Ascend310P to accelerate F32 and F16 LLM Model

Author

leo-pony

Parents

a5e47592

Files7

ggml/src/ggml-cann
- CMakeLists.txt
- aclnn_ops.cpp
- kernels
  - CMakeLists.txt
  - dup.cpp
  - get_row_f16.cpp
  - get_row_f32.cpp
  - get_row_q4_0.cpp

llama.cpp c18610b4 - CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)

llama.cpp
c18610b4 - CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)