]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 6724ef1)
cuda : fix jetson compile error (#4560)
authorFantasyGmm <redacted>
Fri, 22 Dec 2023 15:11:12 +0000 (23:11 +0800)
committerGitHub <redacted>
Fri, 22 Dec 2023 15:11:12 +0000 (17:11 +0200)
commita55876955b1a83464171de8d578d3ab062a7b62d
tree38b9d438a1fc56f3d2f53966673f42a2c70ae2f6tree
parent6724ef16573ec7ecce620be56cbbff145856b2fbcommit | diff
cuda : fix jetson compile error (#4560)

* fix old jetson compile error

* Update Makefile

* update jetson detect and cuda version detect

* update cuda marco define

* update makefile and cuda,fix some issue

* Update README.md

Co-authored-by: Georgi Gerganov <redacted>
* Update Makefile

* Update README.md

---------

Co-authored-by: Georgi Gerganov <redacted>
Makefile diff | blob | history
README.md diff | blob | history
ggml-cuda.cu diff | blob | history
ggml-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp