Releases: Green-Sky/llama.cpp
Releases · Green-Sky/llama.cpp
b6022
b5986
sched : fix multiple evaluations of the same graph with pipeline para…
b4823
ggml : portability fixes for VS 2017 (#12150) * Add include files for std::min/max and std::toupper/tolower * win32: move _USE_MATH_DEFINES before includes to ensure M_PI is defined * Use GGML_RESTRICT instead of "restrict" keyword everywhere, and use "__restrict" in MSVC plain C mode * win32: only use __restrict in MSVC if C11/C17 support is not enabled --------- Co-authored-by: Marcus Groeber <[email protected]>
b4822
readme : fix roadmap link (#12185)
b4766
gguf_convert_endian.py: implement byteswapping for q4_k and q6_k (#11…
b1428
batched-bench : print params at start
b1255
ci : switch cudatoolkit install on windows to networked (#3236)
ci_cuda_window_network-b1254-bfab8ee
ci : switch cudatoolkit install on windows to networked
ci_cublas_linux-b1104-cec628e
temporarily disable broken 512 build
ci_cublas_linux-b1071-5562e3e
temporarily disable broken 512 build