 Johannes Gäßler
|
2c9380dd2f
Only one CUDA stream per device for async compute (#1898)
|
2 лет назад |
 Georgi Gerganov
|
051e1b0e6a
llama : fix kv_cache `n` init (close #1903)
|
2 лет назад |
 DaniAndTheWeb
|
86c7571864
make : update for latest Arch (#1701)
|
2 лет назад |
 Howard Su
|
3d59ec5935
ggml : fix warnings under MSVC (#1908)
|
2 лет назад |
 Aaron Miller
|
0711a5f6dc
metal : add norm, cpy f16->f16, alibi kernels (#1823)
|
2 лет назад |
 Faez Shakil
|
fc45a81bc6
exposed modules so that they can be invoked by nix run github:ggerganov/llama.cpp#server etc (#1863)
|
2 лет назад |
 Randall Fitzgerald
|
794db3e7b9
Server Example Refactor and Improvements (#1570)
|
2 лет назад |
 Jiří Podivín
|
5ddf7ea1fb
hooks : setting up flake8 and pre-commit hooks (#1681)
|
2 лет назад |
 Gustavo Rocha Dias
|
bac19927c3
readme : alternative way to build for Android with CLBlast. (#1828)
|
2 лет назад |
 Kerfuffle
|
b4c6f46f17
Allow cmake to build ggml as a library (#1896)
|
2 лет назад |
 David Yang
|
92f20d9942
train : get raw text instead of page with html (#1905)
|
2 лет назад |
 0cc4m
|
d411968e99
opencl : support k-quants (#1836)
|
2 лет назад |
 SuperUserNameMan
|
b41b4cad6f
examples : add "simple" (#1840)
|
2 лет назад |
 Zenix
|
13fe9d2d84
cmake : add auto detection of BLAS_INCLUDE_DIRS (#1886)
|
2 лет назад |
|
Johannes Gäßler
|
ac3b886953
llama : fix embd when offloading non-repeating layers (#1891)
|
2 лет назад |
 FrankHB
|
5b9ccaf104
Fixed possible macro redefinition (#1892)
|
2 лет назад |
 Borislav Stanimirov
|
9cbf50c041
build : fix and ignore MSVC warnings (#1889)
|
2 лет назад |
 Kawrakow
|
3d01122610
CUDA : faster k-quant dot kernels (#1862)
|
2 лет назад |
|
Borislav Stanimirov
|
602c748863
gitignore : add several entries specific to Visual Studio (#1888)
|
2 лет назад |
|
Johannes Gäßler
|
a09f9195be
Fixed CUDA runtime version check (#1879)
|
2 лет назад |
|
Georgi Gerganov
|
bed9275617
cmake : remove whitespaces
|
2 лет назад |
 yangli2
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
2 лет назад |
 Igor Okulist
|
3559433fec
cmake : set include path for OpenBlas (#1830)
|
2 лет назад |
 Frederik Vogel
|
69b34a0e80
swift : Package compile breaks due to ggml-metal.metal (#1831)
|
2 лет назад |
 daboe01
|
cf267d1c71
make : add train-text-from-scratch (#1850)
|
2 лет назад |
 Srinivas Billa
|
9dda13e5e1
readme : server compile flag (#1874)
|
2 лет назад |
 sandyiscool
|
37e257c48e
make : clean *.so files (#1857)
|
2 лет назад |
|
Howard Su
|
64cc19b4fe
Fix the validation of main device (#1872)
|
2 лет назад |
|
Georgi Gerganov
|
4bfcc855ab
metal : parallel command buffer encoding (#1860)
|
2 лет назад |
|
Johannes Gäßler
|
6b8312e797
Better error when using both LoRA + GPU layers (#1861)
|
2 лет назад |
