]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#12000)
authorGian-Carlo Pascutto <redacted>
Sat, 22 Feb 2025 08:43:24 +0000 (09:43 +0100)
committerGitHub <redacted>
Sat, 22 Feb 2025 08:43:24 +0000 (09:43 +0100)
commitd70908421ff22b013e8209f2d12e5c750663c620
tree04ded2db8b37b40d4ed643e54a5e25aafbf9385d
parentde8b5a3624499bdb9fa6e99840259998638f093f
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#12000)
ggml/src/ggml-cuda/cpy.cu
ggml/src/ggml-cuda/ggml-cuda.cu