 Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
2 жил өмнө |
 Jared Van Bortel
|
511f52c334
build : enable libstdc++ assertions for debug builds (#4275)
|
2 жил өмнө |
 Li Tan
|
f7f9e06212
cmake : fix the metal file foder path (#4217)
|
2 жил өмнө |
 bandoti
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
2 жил өмнө |
 Roger Meier
|
8e9361089d
build : support ppc64le build for make and CMake (#3963)
|
2 жил өмнө |
 Michael Potter
|
6bb4908a17
Fix MacOS Sonoma model quantization (#4052)
|
2 жил өмнө |
 Eve
|
c41ea36eaa
cmake : MSVC instruction detection (fixed up #809) (#3923)
|
2 жил өмнө |
 slaren
|
21958bb393
cmake : disable LLAMA_NATIVE by default (#3906)
|
2 жил өмнө |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 жил өмнө |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
2 жил өмнө |
|
Georgi Gerganov
|
2f9ec7e271
cuda : improve text-generation and batched decoding performance (#3776)
|
2 жил өмнө |
|
Georgi Gerganov
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
2 жил өмнө |
|
Georgi Gerganov
|
d28e572c02
cmake : fix add_compile_options on macOS
|
2 жил өмнө |
|
Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
2 жил өмнө |
|
Eve
|
017efe899d
cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
|
2 жил өмнө |
|
cebtenzzre
|
e78f0b0d05
cmake : increase minimum version for add_link_options (#3444)
|
2 жил өмнө |
|
cebtenzzre
|
9476b01226
cmake : make CUDA flags more similar to the Makefile (#3420)
|
2 жил өмнө |
|
bandoti
|
095231dfd3
cmake : fix transient definitions in find pkg (#3411)
|
2 жил өмнө |
|
Cebtenzzre
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
2 жил өмнө |
 Jag Chadha
|
527e57cfd8
build : add ACCELERATE_NEW_LAPACK to fix warning on macOS Sonoma (#3342)
|
2 жил өмнө |
 DAN™
|
99115f3fa6
cmake : fix build-info.h on MSVC (#3309)
|
2 жил өмнө |
 Johannes Gäßler
|
111163e246
CUDA: enable peer access between devices (#2470)
|
2 жил өмнө |
|
Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 жил өмнө |
 Engininja2
|
7e50d34be6
cmake : fix building shared libs for clang (rocm) on windows (#3176)
|
2 жил өмнө |
 Andrei
|
76164fe2e6
cmake : fix llama.h location when built outside of root directory (#3179)
|
2 жил өмнө |
|
Andrei
|
769266a543
cmake : compile ggml-rocm with -fpic when building shared library (#3158)
|
2 жил өмнө |
|
bandoti
|
990a5e226a
cmake : add relocatable Llama package (#2960)
|
2 жил өмнө |
 Tristan Ross
|
1b6c650d16
cmake : add a compiler flag check for FP16 format (#3086)
|
2 жил өмнө |
|
Johannes Gäßler
|
0a5eebb45d
CUDA: mul_mat_q RDNA2 tunings (#2910)
|
2 жил өмнө |
 Eric Sommerlade
|
b52b29ab9d
arm64 support for windows (#3007)
|
2 жил өмнө |
