]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
SYCL : SOFTMAX F16 mask support and other fixes (llama/11261)
authorAkarshan Biswas <redacted>
Tue, 28 Jan 2025 09:56:58 +0000 (15:26 +0530)
committerGeorgi Gerganov <redacted>
Wed, 29 Jan 2025 10:57:00 +0000 (12:57 +0200)
commitf8e8749eaf984dc1b47d976098696cdf421c4cf8
tree36069fbb55552de61745e605290d4a01b54f648d
parent53c2ce7a9a044ea16a6173cf62d646030d46ef21
SYCL : SOFTMAX F16 mask support and other fixes (llama/11261)

Implemented ggml_sycl_op_soft_max() F16 src1(mask) support for which a pragma deprecation warning was added during #5021.
To do this, had to decouple it from ggml_sycl_op_flatten which always considered src1 to be of fp32 type(many OP functions are dependent on it).

* SYCL: SOFTMAX F16 mask support and other fixes

* test-backend-ops: Add F16 mask test cases
src/ggml-sycl/ggml-sycl.cpp
src/ggml-sycl/softmax.cpp
src/ggml-sycl/softmax.hpp
tests/test-backend-ops.cpp