]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CANN: Add the basic supports of Flash Attention kernel (#13627)
authorBizhao Shi <redacted>
Mon, 26 May 2025 02:20:18 +0000 (10:20 +0800)
committerGitHub <redacted>
Mon, 26 May 2025 02:20:18 +0000 (10:20 +0800)
commit2d38b6e4004fb1c341723e657fb1e71a4d3fb473
tree3c4eb6c918a68364c99103a0cf1ebadd31b8a2d2
parente121edc4324a640be11b7e567edd39b721b0f8e4
CANN: Add the basic supports of Flash Attention kernel (#13627)

* cann: add the basic FA support

* cann: update the readme

* cann: update the FlashAttention with PSEShift

* cann: update the input parameters in FA

* cann: update the alibi with max_bias

* cann: add the constrints of softcap

* cann: update the docs CANN.md

* cann: update the docs CANN.md

* cann: fix typo of CANN.md

* cann: add some comments and update the CANN.md

* cann: update the CANN.md

* cann: update the inner precise for fusedInferAttention

* cann: update the constraints of flash_attn_ext on ggml-cann.cpp

* cann: clean the whitespace

* cann: clean the whitespace

* cann: add a new endline
docs/backend/CANN.md [changed mode: 0644->0755]
ggml/src/ggml-cann/CMakeLists.txt [changed mode: 0644->0755]
ggml/src/ggml-cann/Doxyfile [changed mode: 0644->0755]
ggml/src/ggml-cann/acl_tensor.cpp [changed mode: 0644->0755]
ggml/src/ggml-cann/acl_tensor.h [changed mode: 0644->0755]
ggml/src/ggml-cann/aclnn_ops.cpp [changed mode: 0644->0755]
ggml/src/ggml-cann/aclnn_ops.h [changed mode: 0644->0755]
ggml/src/ggml-cann/common.h [changed mode: 0644->0755]
ggml/src/ggml-cann/ggml-cann.cpp [changed mode: 0644->0755]