Releases: ggerganov/llama.cpp
Releases · ggerganov/llama.cpp
b3883
sync : ggml
b3880
ci : fine-grant permission (#9710)
b3879
Fixed RNG seed docs (#9723) * Update README.md fixed RNG seed info * changed print format to unsigned
b3878
metal : remove abort (skip) (ggml/0)
b3874
metal : fix compute pass descriptor autorelease crash (#9718)
b3873
ggml-backend : add device description to CPU backend (#9720)
b3872
ggml: unify backend logging mechanism (#9709) * Add scaffolding for ggml logging macros * Metal backend now uses GGML logging * Cuda backend now uses GGML logging * Cann backend now uses GGML logging * Add enum tag to parameters * Use C memory allocation funcs * Fix compile error * Use GGML_LOG instead of GGML_PRINT * Rename llama_state to llama_logger_state * Prevent null format string * Fix whitespace * Remove log callbacks from ggml backends * Remove cuda log statement
b3870
rpc : enable vulkan (#9714) closes #8536
b3869
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)
b3868
ggml-backend : add device and backend reg interfaces (#9707) Co-authored-by: Johannes Gäßler <[email protected]>