]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: aede207)
Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml...
authorcmdr2 <redacted>
Tue, 25 Feb 2025 12:36:34 +0000 (18:06 +0530)
committerGeorgi Gerganov <redacted>
Mon, 3 Mar 2025 16:18:11 +0000 (18:18 +0200)
commitf54a4ba11ed8ab59da778d5e280f7dc73c775a7a
treea28fb537b33d84f45ea743db60e358687755d04ctree
parentaede2074f608d7bf6614cdd047bce687a2b3d908commit | diff
Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121)

* Support float16-to-float16 add/sub/mul/div operations in the CUDA backend

* Add fp16 support for add/sub/mul/div on the CPU backend

* Add test cases for fp16 add/sub/mul/div
ggml/src/ggml-cpu/ggml-cpu.c diff | blob | history
ggml/src/ggml-cuda/binbcast.cu diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp