COMMITS
/ ggml/CMakeLists.txt December 4, 2024
D
ggml : add predefined list of CPU backend variants to build (#10626)
Diego Devesa committed
December 1, 2024
D
ggml : automatic selection of best CPU backend (#10606)
Diego Devesa committed
November 29, 2024
D
ggml : move AMX to the CPU backend (#10570)
Diego Devesa committed
November 25, 2024
D
ggml : add support for dynamic loading of backends (#10469)
Diego Devesa committed
November 19, 2024
H
add cmake rvv support (#10411)
haopeng committed
B
Add required ggml-base and backend libs to cmake pkg (#10407)
bandoti committed
R
sycl : Add option to set the SYCL architecture for all targets (#10266)
Romain Biessy committed
November 17, 2024
J
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)
Johannes Gäßler committed
November 16, 2024
J
ggml: new optimization interface (ggml/988)
Johannes Gäßler committed
November 15, 2024
C
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921)
Charles Xu committed
November 14, 2024
D
ggml : build backends as libraries (#10256)
Diego Devesa committed
November 8, 2024
G
metal : opt-in compile flag for BF16 (#10218)
Georgi Gerganov committed
November 7, 2024
D
ggml : add ggml-cpu.h to the public headers (#10204)
Diego Devesa committed
October 18, 2024
M
add amx kernel for gemm (#8998)
Ma Mingfei committed
September 16, 2024
G
cmake : do not hide GGML options + rename option (#9465)
Georgi Gerganov committed
September 6, 2024
M
Improve Vulkan shader build system (#9239)
Markus Tavenrath committed
August 14, 2024
0
Vulkan Optimizations and Fixes (#8959)
0cc4m committed
G
cmake : remove unused option GGML_CURL (#9011)
Georgi Gerganov committed
July 30, 2024
W
cann: update cmake (#8765)
wangshuai09 committed
July 27, 2024
R
feat: Support Moore Threads GPU (#8383)
R0CKSTAR committed
July 12, 2024
B
cmake : only enable GGML_NATIVE and x86 flags if not crosscompiling (ggml/885)
Borislav Stanimirov committed
July 18, 2024
6
cmake : install all ggml public headers (#8480)
65a committed
July 10, 2024
G
ggml : move sgemm sources to llamafile subfolder (#8394)
Georgi Gerganov committed
June 26, 2024
S
G
llama : reorganize source code + improve CMake (#8006)
Georgi Gerganov committed