Jeffrey Morgan d10d3aac58 disable execstack for amd libraries 1 rok temu
..
ext_server 1ffb1e2874 update llama.cpp submodule to `77d1ac7` (#3030) 1 rok temu
generate d10d3aac58 disable execstack for amd libraries 1 rok temu
llama.cpp @ 77d1ac7e00 1ffb1e2874 update llama.cpp submodule to `77d1ac7` (#3030) 1 rok temu
patches 908005d90b patch: use default locale in wpm tokenizer (#3034) 1 rok temu
dyn_ext_server.c 6c5ccb11f9 Revamp ROCm support 1 rok temu
dyn_ext_server.go 6c5ccb11f9 Revamp ROCm support 1 rok temu
dyn_ext_server.h 39928a42e8 Always dynamically load the llm server library 1 rok temu
ggla.go 76bdebbadf decode ggla 1 rok temu
ggml.go 76bdebbadf decode ggla 1 rok temu
gguf.go 76bdebbadf decode ggla 1 rok temu
llama.go f11bf0740b use `llm.ImageData` 1 rok temu
llm.go f9cd55c70b disable gpu for certain model architectures and fix divide-by-zero on memory estimation 1 rok temu
payload_common.go 1ffb1e2874 update llama.cpp submodule to `77d1ac7` (#3030) 1 rok temu
payload_darwin_amd64.go 1ffb1e2874 update llama.cpp submodule to `77d1ac7` (#3030) 1 rok temu
payload_darwin_arm64.go 1b249748ab Add multiple CPU variants for Intel Mac 1 rok temu
payload_linux.go 6c5ccb11f9 Revamp ROCm support 1 rok temu
payload_test.go 7427fa1387 Fix up the CPU fallback selection 1 rok temu
payload_windows.go 1b249748ab Add multiple CPU variants for Intel Mac 1 rok temu
utils.go fccf8d179f partial decode ggml bin for more info 1 rok temu