tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-09 21:10:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CANN] Add Ascend NPU backend (#6035)

Browse Source 
* [CANN] Add Ascend NPU backend

Ascend is a full-stack AI computing infrastructure for industry
applications and services based on Huawei Ascend processors and
software.

CANN (Compute Architecture of Neural Networks), developped by
Huawei, is a heterogeneous computing architecture for AI.

Co-authored-by: wangshuai09 <391746016@qq.com>

* delete trailing whitespaces

* Modify the code based on review comment

* Rename LLAMA_CANN to GGML_CANN

* Make ggml-common.h private

* add ggml_cann prefix for acl funcs

* Add logging for CANN backend

* Delete Trailing whitespace

---------

Co-authored-by: wangshuai09 <391746016@qq.com>
This commit is contained in:
hipudding
2024-07-17 19:23:50 +08:00
committed by GitHub
parent da3913d8f9
commit 1bdd8ae19f
27 changed files with 10756 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/include/ggml.h
View File

@ -753,6 +753,8 @@ extern "C" {
GGML_API bool ggml_are_same_shape (const struct ggml_tensor * t0, const struct ggml_tensor * t1);
GGML_API bool ggml_are_same_stride(const struct ggml_tensor * t0, const struct ggml_tensor * t1);
GGML_API bool ggml_can_repeat(const struct ggml_tensor * t0, const struct ggml_tensor * t1);
// use this to compute the memory overhead of a tensor
GGML_API size_t ggml_tensor_overhead(void);
@ -2397,6 +2399,7 @@ extern "C" {
GGML_API int ggml_cpu_has_rpc (void);
GGML_API int ggml_cpu_has_vsx (void);
GGML_API int ggml_cpu_has_matmul_int8(void);
GGML_API int ggml_cpu_has_cann (void);
//
// Internal types and functions exposed for tests and benchmarks