 Alon
|
a40f2b656f
CI: FreeBSD fix (#3258)
|
2 years ago |
 Georgi Gerganov
|
d119c04c15
examples : fix benchmark-matmult (#1554)
|
2 years ago |
 Cebtenzzre
|
8781013ef6
make : restore build-info.h dependency for several targets (#3205)
|
2 years ago |
 Erik Scholz
|
7ddf185537
ci : switch cudatoolkit install on windows to networked (#3236)
|
2 years ago |
 Johannes Gäßler
|
ee66942d7e
CUDA: fix peer access logic (#3231)
|
2 years ago |
|
Johannes Gäßler
|
111163e246
CUDA: enable peer access between devices (#2470)
|
2 years ago |
 slaren
|
8b428c9bc8
llama.cpp : show model size and BPW on load (#3223)
|
2 years ago |
|
Johannes Gäßler
|
578d8c8f5c
CUDA: fix scratch malloced on non-main device (#3220)
|
2 years ago |
 IsaacDynamo
|
b541b4f0b1
Enable BUILD_SHARED_LIBS=ON on all Windows builds (#3215)
|
2 years ago |
 Vlad
|
5dbc2b3213
Enable build with CUDA 11.0 (make) (#3132)
|
2 years ago |
 goerch
|
b08e75baea
Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)
|
2 years ago |
|
Cebtenzzre
|
e6616cf0db
examples : add compiler version and target to build info (#2998)
|
2 years ago |
|
Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 years ago |
|
Cebtenzzre
|
69eb67e282
fix build numbers by setting fetch-depth=0 (#3197)
|
2 years ago |
 Meng Zhang
|
4fe09dfe66
llama : add support for StarCoder model architectures (#3187)
|
2 years ago |
|
Cebtenzzre
|
80291a1d02
common : do not use GNU zero-length __VA_ARGS__ extension (#3195)
|
2 years ago |
|
Georgi Gerganov
|
c6f1491da0
metal : fix bug in soft_max kernels (out-of-bounds access) (#3194)
|
2 years ago |
|
Cebtenzzre
|
e3d87a6c36
convert : make ftype optional in simple scripts (#3185)
|
2 years ago |
|
Georgi Gerganov
|
8c00b7a6ff
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)
|
2 years ago |
 Engininja2
|
7e50d34be6
cmake : fix building shared libs for clang (rocm) on windows (#3176)
|
2 years ago |
 Evgeny Kurnevsky
|
235f7c193b
flake : use pkg-config instead of pkgconfig (#3188)
|
2 years ago |
|
Georgi Gerganov
|
a51b687657
metal : relax conditions on fast matrix multiplication kernel (#3168)
|
2 years ago |
 Andrei
|
76164fe2e6
cmake : fix llama.h location when built outside of root directory (#3179)
|
2 years ago |
 Ali Tariq
|
c2ab6fe661
ci : Cloud-V for RISC-V builds (#3160)
|
2 years ago |
 Roland
|
2d770505a8
llama : remove mtest (#3177)
|
2 years ago |
|
Cebtenzzre
|
98311c4277
llama : make quantize example up to 2.7x faster (#3115)
|
2 years ago |
 jneem
|
feea179e9f
flake : allow $out/include to already exist (#3175)
|
2 years ago |
|
Andrei
|
769266a543
cmake : compile ggml-rocm with -fpic when building shared library (#3158)
|
2 years ago |
 Asbjørn Olling
|
cf8238e7f4
flake : include llama.h in nix output (#3159)
|
2 years ago |
|
Cebtenzzre
|
4b8560e72a
make : fix clang++ detection, move some definitions to CPPFLAGS (#3155)
|
2 years ago |
