]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 834695f)
Improve cuBLAS performance by dequantizing on the GPU (#1065)
authorslaren <redacted>
Thu, 20 Apr 2023 01:14:14 +0000 (03:14 +0200)
committerGitHub <redacted>
Thu, 20 Apr 2023 01:14:14 +0000 (03:14 +0200)
commit02d6988121510c067e06d498a273a351a888f5b9
tree98c6204ad4f3db40bc49595bb7705e8bcd699e5dtree
parent834695fe3a3ed2a962e774c9615e3f7b41d360a8commit | diff
Improve cuBLAS performance by dequantizing on the GPU (#1065)
CMakeLists.txt diff | blob | history
Makefile diff | blob | history
ggml-cuda.cu [new file with mode: 0644] blob
ggml-cuda.h [new file with mode: 0644] blob
ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp