]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 25d7abb)
Improve cuBLAS performance by using a memory pool (#1094)
authorslaren <redacted>
Fri, 21 Apr 2023 19:59:17 +0000 (21:59 +0200)
committerGitHub <redacted>
Fri, 21 Apr 2023 19:59:17 +0000 (21:59 +0200)
commit50cb666b8a2e35a49b08c0f6bc81138c8f6f2ac1
tree80370baa4d8b17d2cb44a134bed6b1a088b1cfc1tree
parent25d7abbd1f73582b7e0fdc422a936e8541c0780bcommit | diff
Improve cuBLAS performance by using a memory pool (#1094)

* Improve cuBLAS performance by using a memory pool

* Move cuda specific definitions to ggml-cuda.h/cu

* Add CXX flags to nvcc

* Change memory pool synchronization mechanism to a spin lock
General code cleanup
Makefile diff | blob | history
ggml-cuda.cu diff | blob | history
ggml-cuda.h diff | blob | history
ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp