]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: ee1a0ec)
llama : allow quantizing k-quants to fall back when tensor size incompatible (#3747)
authorKerfuffle <redacted>
Sat, 28 Oct 2023 11:54:24 +0000 (05:54 -0600)
committerGitHub <redacted>
Sat, 28 Oct 2023 11:54:24 +0000 (14:54 +0300)
commitbd6d9e205982b34e0ba2c3b22bbf31a1ef1a1bb5
tree6fad32920bf28081145c17cddf5f7597e3a0b2f6tree
parentee1a0ec9cb367ba41d138134795cbbbe93d2bf1ccommit | diff
llama : allow quantizing k-quants to fall back when tensor size incompatible (#3747)

* Allow quantizing k-quants to fall back when tensor size incompatible

* quantizing: Add warning when tensors were incompatible with k-quants

Clean up k-quants state passing a bit
llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp