]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b24c304)
Convert vector to f16 for dequantize mul mat vec (#1913)
authorJohannes Gäßler <redacted>
Mon, 19 Jun 2023 08:23:56 +0000 (10:23 +0200)
committerGitHub <redacted>
Mon, 19 Jun 2023 08:23:56 +0000 (10:23 +0200)
commit16b9cd193965769089881bb8ec012fccca7b37b6
tree2ee329793e782f253966fd81f89ea05f5a1a2495tree
parentb24c3049d96557c24782e4d32feaae65f47277afcommit | diff
Convert vector to f16 for dequantize mul mat vec (#1913)

* Convert vector to f16 for dmmv

* compile option

* Added compilation option description to README

* Changed cmake CUDA_ARCHITECTURES from "OFF" to "native"
CMakeLists.txt diff | blob | history
Makefile diff | blob | history
README.md diff | blob | history
ggml-cuda.cu diff | blob | history
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp