]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: da3913d)
[CANN] Add Ascend NPU backend (#6035)
authorhipudding <redacted>
Wed, 17 Jul 2024 11:23:50 +0000 (19:23 +0800)
committerGitHub <redacted>
Wed, 17 Jul 2024 11:23:50 +0000 (14:23 +0300)
commit1bdd8ae19f50bc6f108fa247e90688e5c60559fc
tree8548bb02cc5f5176579a35c73697cbd3938ea28ctree
parentda3913d8f9475b0d4bcbeb4936c724af4eade092commit | diff
[CANN] Add Ascend NPU backend (#6035)

* [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 <redacted>
* 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 <redacted>
27 files changed:
CMakeLists.txt diff | blob | history
examples/llama-bench/llama-bench.cpp diff | blob | history
examples/llava/clip.cpp diff | blob | history
ggml/include/ggml-cann.h [new file with mode: 0644] blob
ggml/include/ggml.h diff | blob | history
ggml/src/CMakeLists.txt diff | blob | history
ggml/src/ggml-backend.c diff | blob | history
ggml/src/ggml-cann.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/.clang-format [new file with mode: 0644] blob
ggml/src/ggml-cann/Doxyfile [new file with mode: 0644] blob
ggml/src/ggml-cann/acl_tensor.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/acl_tensor.h [new file with mode: 0644] blob
ggml/src/ggml-cann/aclnn_ops.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/aclnn_ops.h [new file with mode: 0644] blob
ggml/src/ggml-cann/common.h [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/CMakeLists.txt [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/ascendc_kernels.h [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/dup.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/get_row_f16.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/get_row_f32.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/get_row_q4_0.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/get_row_q8_0.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/quantize_f16_q8_0.cpp [new file with mode: 0644] blob
ggml/src/ggml-cann/kernels/quantize_f32_q8_0.cpp [new file with mode: 0644] blob
ggml/src/ggml.c diff | blob | history
src/llama.cpp diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp