 Kawrakow
|
e68c96f7fe
Faster Q2_K on Metal (#2297)
|
2 年之前 |
 Przemysław Pawełczyk
|
9cf022a188
make : fix embdinput library and server examples building on MSYS2 (#2235)
|
2 年之前 |
|
Kawrakow
|
e782c9e735
Faster Q5_K and Q6_K on Metal (#2294)
|
2 年之前 |
|
Kawrakow
|
785829dfe8
Faster Q4_K on Metal (#2290)
|
2 年之前 |
 Georgi Gerganov
|
fff0e0eafe
llama : fix regression from #2000 - could not load no-mmap models
|
2 年之前 |
 Shouzheng Liu
|
417a85a001
metal: minor q4 optimization and reduce code size (#2248)
|
2 年之前 |
 Rinne
|
294f424554
llama : extend API to get max devices at runtime (#2253)
|
2 年之前 |
 wzy
|
45a1b07e9b
flake : update flake.nix (#2270)
|
2 年之前 |
|
wzy
|
b1f4290953
cmake : install targets (#2256)
|
2 年之前 |
|
Georgi Gerganov
|
d01bccde9f
ci : integrate with ggml-org/ci (#2250)
|
2 年之前 |
|
Georgi Gerganov
|
6cbf9dfb32
llama : shorten quantization descriptions
|
2 年之前 |
 Jiahao Li
|
7568d1a2b2
Support dup & cont ops on CUDA (#2242)
|
2 年之前 |
 Alex Klinkhamer
|
b7647436cc
llama : fix t_start_sample_us initialization warning (#2238)
|
2 年之前 |
 Qingyou Meng
|
672dda10e4
ggml : fixed runtime bugs and compile errors related to GGML_PERF and GGML_DEBUG (#2219)
|
2 年之前 |
 Jiří Podivín
|
27ab66e437
py : turn verify-checksum-models.py into executable (#2245)
|
2 年之前 |
 Xiao-Yong Jin
|
6e7cca4047
llama : add custom RoPE (#2054)
|
2 年之前 |
 Dave Della Costa
|
a6803cab94
flake : add runHook preInstall/postInstall to installPhase so hooks function (#2224)
|
2 年之前 |
|
wzy
|
7dabc66f3c
make : use pkg-config for OpenBLAS (#2222)
|
2 年之前 |
 Bach Le
|
7cdd30bf1f
cuda : allocate all temporary ggml_tensor_extra_gpu from a fixed-size buffer (#2220)
|
2 年之前 |
 Evan Miller
|
e8035f141e
ggml : fix static_assert with older compilers #2024 (#2218)
|
2 年之前 |
|
Bach Le
|
7513b7b0a1
llama : add functions that work directly on model (#2197)
|
2 年之前 |
 Ali Chraghi
|
de8342423d
build.zig : install config header (#2216)
|
2 年之前 |
 Shangning Xu
|
c48c525f87
examples : fixed path typos in embd-input (#2214)
|
2 年之前 |
|
Jiahao Li
|
206e01de11
cuda : support broadcast add & mul (#2192)
|
2 年之前 |
 Johannes Gäßler
|
4304bd3cde
CUDA: mul_mat_vec_q kernels for k-quants (#2203)
|
2 年之前 |
 James Reynolds
|
229aab351c
make : fix combination of LLAMA_METAL and LLAMA_MPI (#2208)
|
2 年之前 |
|
Georgi Gerganov
|
697966680b
ggml : sync (ggml_conv_2d, fix mul_mat bug, CUDA GLM rope)
|
2 年之前 |
|
Kawrakow
|
27ad57a69b
Metal: faster Q4_0 and Q4_1 matrix x vector kernels (#2212)
|
2 年之前 |
 Howard Su
|
32c5411631
Revert "Support using mmap when applying LoRA (#2095)" (#2206)
|
2 年之前 |
|
Howard Su
|
ff5d58faec
Fix compile error on Windows CUDA (#2207)
|
2 年之前 |
