]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3413ae2)
kompute : implement op_getrows_f32 (#6403)
authorwoachk <redacted>
Mon, 3 Jun 2024 05:32:16 +0000 (07:32 +0200)
committerGitHub <redacted>
Mon, 3 Jun 2024 05:32:16 +0000 (08:32 +0300)
commit9e405b6e2ecb888e860f7b92720b4809e21b3915
treee42d87168def2b7a21a003253720a79d743f4c3btree
parent3413ae2193d0693f14bead02e5018f442cbf579bcommit | diff
kompute : implement op_getrows_f32 (#6403)

op_getrows_f32 is required since https://github.com/ggerganov/llama.cpp/pull/6122
for the Vulkan w/ Kompute backend to be functional.

As such, implement this op to make this backend functional again.
CMakeLists.txt diff | blob | history
ggml-kompute.cpp diff | blob | history
kompute-shaders/op_getrows_f32.comp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp