]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: d5512b7)
Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)
authorKawrakow <redacted>
Tue, 25 Jul 2023 10:48:04 +0000 (13:48 +0300)
committerGitHub <redacted>
Tue, 25 Jul 2023 10:48:04 +0000 (13:48 +0300)
commit129d844c87d90e74aafc23dcc84c980fd408def4
tree7f47d3436ac64384eaf6f548f3f2406b38fce39dtree
parentd5512b782b27ff698007dcd175da18959d5f163fcommit | diff
Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)

* Fix Q4_K and Q5_K for QK_K = 64

* Very slightly better Q5_K bit fiddling

---------

Co-authored-by: Iwan Kawrakow <redacted>
ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp