Releases: Xarbirus/llama.cpp
Releases · Xarbirus/llama.cpp
b2296
llama : constified `llama_set_state_data`'s `src` (#5774)
b2291
sync : ggml
b2277
Makefile: use variables for cublas (#5689) * make: use arch variable for cublas * fix UNAME_M * check opt first --------- Co-authored-by: lindeer <[email protected]>
b2271
unicode : reuse iterator (#5726)
b2270
server: CI fix trailing space (#5728)
b2099
Merge branch 'ggerganov:master' into master
b2094
fix `error C2078: too many initializers` with uint32x4_t for MSVC ARM64
b2093
CUDA: fixed mmvq kernel for bs 2,3,4 and -sm row (#5386)
b1354
sync : ggml (ggml-backend) (#3548) * sync : ggml (ggml-backend) ggml-ci * zig : add ggml-backend to the build