ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-16 22:08:07 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Add Ascend NPU backend (llama/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 Georgi Gerganov
parent fcba6aa352
commit 8923bb4292
4 changed files with 87 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml.c
View File

@ -3341,7 +3341,7 @@ bool ggml_are_same_stride(const struct ggml_tensor * t0, const struct ggml_tenso
}
// check if t1 can be represented as a repeatition of t0
static inline bool ggml_can_repeat(const struct ggml_tensor * t0, const struct ggml_tensor * t1) {
bool ggml_can_repeat(const struct ggml_tensor * t0, const struct ggml_tensor * t1) {
static_assert(GGML_MAX_DIMS == 4, "GGML_MAX_DIMS is not 4 - update this function");
return ggml_is_empty(t0) ? ggml_is_empty(t1) :
@ -13699,6 +13699,7 @@ static void ggml_compute_forward_soft_max(
}
}
// ggml_compute_forward_soft_max_back
static void ggml_compute_forward_soft_max_back_f32(
@ -21994,6 +21995,14 @@ int ggml_cpu_has_rpc(void) {
#endif
}
int ggml_cpu_has_cann(void) {
#if defined(GGML_USE_CANN)
return 1;
#else
return 0;
#endif
}
int ggml_cpu_has_gpublas(void) {
return ggml_cpu_has_cuda() || ggml_cpu_has_vulkan() || ggml_cpu_has_kompute() || ggml_cpu_has_sycl();
}