 Georgi Gerganov
|
17c10acfb4
ggml : force no_alloc == false when creating opt tensors (close #1699)
|
2 years ago |
 Kawrakow
|
e9b66ee982
metal : add Q4_1 implementation (#1785)
|
2 years ago |
 Kerfuffle
|
4f0154b0ba
llama : support requantizing models instead of only allowing quantization from 16/32bit (#1691)
|
2 years ago |
 Xingchen Song(宋星辰)
|
ef3171d162
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 (#1638)
|
2 years ago |
 rankaiyx
|
555275a693
make : add SSSE3 compilation use case (#1659)
|
2 years ago |
 Robert Sung-wook Shin
|
98ed165574
OpenCL: Add release memory (#1741)
|
2 years ago |
 Johannes Gäßler
|
ae9663f188
Windows nvcc workaround (#1753)
|
2 years ago |
|
Georgi Gerganov
|
b33dee282f
metal : fix build "tanhf" -> "tanh"
|
2 years ago |
 AT
|
92f44ff7f7
metal : add GELU implementation (#1770)
|
2 years ago |
|
Kawrakow
|
245fc3c37d
metal : faster q4_0 (#1775)
|
2 years ago |
|
Kawrakow
|
72ff5282bf
metal : add Q2_K implementation (#1762)
|
2 years ago |
|
Georgi Gerganov
|
0bf7cf1b29
Revert "ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)"
|
2 years ago |
 le.chang
|
8432d4d9f7
ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)
|
2 years ago |
|
Kawrakow
|
0f291e1f65
metal : Q6_K implementation (#1752)
|
2 years ago |
 qingfengfenga
|
8fc8179919
Add llama.cpp docker support for non-latin languages (#1673)
|
2 years ago |
 Steven Roussey
|
b50b570ed9
ggml : fix fprintf warnings (#1720)
|
2 years ago |
|
Georgi Gerganov
|
53aba3f393
clang-tidy : restore dot file from accidental deletion
|
2 years ago |
|
Kawrakow
|
4161bdc04d
metal : add Q4_K implementation (#1733)
|
2 years ago |
 johnson442
|
0035858273
k-quants : add missing compile definition to CMakeLists (#1748)
|
2 years ago |
|
Georgi Gerganov
|
5c64a0952e
k-quants : allow to optionally disable at compile time (#1734)
|
2 years ago |
 jacobi petrucciani
|
5b57a5b726
flake : update to support metal on m1/m2 (#1724)
|
2 years ago |
|
Georgi Gerganov
|
4dc62c545d
readme : add June roadmap
|
2 years ago |
 Willy Tarreau
|
35a84916fb
main: add the possibility to open the prompt cache read-only (#1640)
|
2 years ago |
|
Georgi Gerganov
|
2d7bf110ed
llama : fix vram_scratch var
|
2 years ago |
|
Georgi Gerganov
|
2a4e41a086
llama : fix compile warnings
|
2 years ago |
|
Johannes Gäßler
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
2 years ago |
|
Georgi Gerganov
|
44f906e853
metal : add f16 support
|
2 years ago |
 LostRuins
|
d5b111f53d
Clblast fixes + enhancements to save VRAM and offload more layers (#1675)
|
2 years ago |
|
Georgi Gerganov
|
2d43387daf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)
|
2 years ago |
|
Georgi Gerganov
|
7ad7750c5c
gitignore : add .clang-tidy
|
2 years ago |
