 Herman Semenov
|
77bc1bbd05
cmake : add support for ccache (#5002)
|
пре 2 година |
 Georgi Gerganov
|
9b6ea4263a
cmake : add ggml public headers (#5011)
|
пре 2 година |
 ngc92
|
3e5ca7931c
pass cpu-architecture arguments only to host code (C;C++) (#4943)
|
пре 2 година |
 Karthik Kumar Viswanathan
|
ac32902a87
llama : support WinXP build with MinGW 8.1.0 (#3419)
|
пре 2 година |
 a-n-n-a-l-e-e
|
eec22a1c63
cmake : check for openblas64 (#4134)
|
пре 2 година |
|
Georgi Gerganov
|
91d38876df
metal : switch back to default.metallib (ggml/681)
|
пре 2 година |
|
Georgi Gerganov
|
58ba655af0
metal : enable shader debugging (cmake option) (#4705)
|
пре 2 година |
 slaren
|
5bf3953d7e
cuda : improve cuda pool efficiency using virtual memory (#4606)
|
пре 2 година |
 Erik Garrison
|
0f630fbc92
cuda : ROCm AMD Unified Memory Architecture (UMA) handling (#4449)
|
пре 2 година |
 Bach Le
|
5daa5f54fd
Link to cublas dynamically on Windows even with LLAMA_STATIC (#4506)
|
пре 2 година |
 Jared Van Bortel
|
70f806b821
build : detect host compiler and cuda compiler separately (#4414)
|
пре 2 година |
|
Jared Van Bortel
|
6138963fb2
build : target Windows 8 for standard mingw-w64 (#4405)
|
пре 2 година |
|
Georgi Gerganov
|
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
|
пре 2 година |
|
Jared Van Bortel
|
511f52c334
build : enable libstdc++ assertions for debug builds (#4275)
|
пре 2 година |
 Li Tan
|
f7f9e06212
cmake : fix the metal file foder path (#4217)
|
пре 2 година |
 bandoti
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
пре 2 година |
 Roger Meier
|
8e9361089d
build : support ppc64le build for make and CMake (#3963)
|
пре 2 година |
 Michael Potter
|
6bb4908a17
Fix MacOS Sonoma model quantization (#4052)
|
пре 2 година |
 Eve
|
c41ea36eaa
cmake : MSVC instruction detection (fixed up #809) (#3923)
|
пре 2 година |
|
slaren
|
21958bb393
cmake : disable LLAMA_NATIVE by default (#3906)
|
пре 2 година |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
пре 2 година |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
пре 2 година |
|
Georgi Gerganov
|
2f9ec7e271
cuda : improve text-generation and batched decoding performance (#3776)
|
пре 2 година |
|
Georgi Gerganov
|
2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749)
|
пре 2 година |
|
Georgi Gerganov
|
d28e572c02
cmake : fix add_compile_options on macOS
|
пре 2 година |
|
Georgi Gerganov
|
db3abcc114
sync : ggml (ggml-backend) (#3548)
|
пре 2 година |
|
Eve
|
017efe899d
cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
|
пре 2 година |
|
cebtenzzre
|
e78f0b0d05
cmake : increase minimum version for add_link_options (#3444)
|
пре 2 година |
|
cebtenzzre
|
9476b01226
cmake : make CUDA flags more similar to the Makefile (#3420)
|
пре 2 година |
|
bandoti
|
095231dfd3
cmake : fix transient definitions in find pkg (#3411)
|
пре 2 година |
