Tags: tobi/llama.cpp
Tags
CI: fix subdirectory path globbing (ggml-org#546) - Changes in subdirectories will now be detecter properly - (Windows-MSVC) AVX512 tests temporarily disabled
py : add temporary script to convert old ggml files to newer version (g… …gml-org#539) Co-authored-by: Jakub Horak <[email protected]>
ggml : introduce structs for the q4 data blocks (ggml-org#356) * Introduce structs for the q4 data blocks * ggml : rename quant struct variables + fix ARM_NEON --------- Co-authored-by: Georgi Gerganov <[email protected]>
Fix usage of F16C intrinsics in AVX code (ggml-org#563) * Fix usage of F16C intrinsics in AVX code when F16C is not defined
all : be more strict about converting float to double (ggml-org#458) * Be more strict about converting float to double * Test equivalence of round, SILU implementations Test module is commented out in CMakeLists.txt because the tests may take a long time, depending on how much the compiler optimizes. * Fix softmax in perplexity.cpp * all : prefer float over double where appropriate * perplexity : add <cmath> --------- Co-authored-by: Georgi Gerganov <[email protected]>
ggml : refactor quantized processing functions (ggml-org#509) * Refactor quantized processing functions * ggml : minor --------- Co-authored-by: Georgi Gerganov <[email protected]>
ci : make ctest verbose, hopefully we see what is wrong with the sani… …tizer
deploy : add a Package.swift for SwiftPM support (ggml-org#393) * Add a Package.swift for SwiftPM support * Swap from exclusions to allowlist
llama : fix linkage with mingw (ggml-org#551) * Revert 7e53955 (ggml-org#542) Still needs to be fixed properly * Fix linking on mingw32
PreviousNext