 Georgi Gerganov
|
0d152b37fe
ggml : fix build after #3329
|
%!s(int64=2) %!d(string=hai) anos |
 ds5t5
|
f8c90cdbaa
llm : add Refact model (#3329)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
f93af02488
sync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
|
%!s(int64=2) %!d(string=hai) anos |
 Tameem
|
79f34abddb
ggml : add RISC-V Vector Support for K-Quants and improved the existing intrinsics (#3453)
|
%!s(int64=2) %!d(string=hai) anos |
 shibe2
|
665018c749
CLBlast: Add broadcast support for matrix multiplication (#3402)
|
%!s(int64=2) %!d(string=hai) anos |
 Cebtenzzre
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
%!s(int64=2) %!d(string=hai) anos |
 Qu Zongfu
|
7f1a0fe709
ggml : release the requested thread pool resource (#3292)
|
%!s(int64=2) %!d(string=hai) anos |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
%!s(int64=2) %!d(string=hai) anos |
|
Cebtenzzre
|
2db94d98ed
gguf : basic type checking in gguf_get_* (#3346)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
8c00b7a6ff
sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
a51b687657
metal : relax conditions on fast matrix multiplication kernel (#3168)
|
%!s(int64=2) %!d(string=hai) anos |
 Eric Sommerlade
|
b52b29ab9d
arm64 support for windows (#3007)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
b3e9852e47
sync : ggml (CUDA GLM RoPE + POSIX) (#3082)
|
%!s(int64=2) %!d(string=hai) anos |
 Przemysław Pawełczyk
|
cb6c44c5e0
build : do not use _GNU_SOURCE gratuitously (#2035)
|
%!s(int64=2) %!d(string=hai) anos |
 Kunshang Ji
|
7f412dab9c
enable CPU HBM (#2603)
|
%!s(int64=2) %!d(string=hai) anos |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
%!s(int64=2) %!d(string=hai) anos |
|
Przemysław Pawełczyk
|
fec2fb19e4
ggml : posixify madvise and pagesize (#3037)
|
%!s(int64=2) %!d(string=hai) anos |
 Jhen-Jie Hong
|
21f3d1be86
k-quants : fix build on armv7 (android only) (#2920)
|
%!s(int64=2) %!d(string=hai) anos |
|
Tameem
|
5aec2cfaac
ggml : add RISC-V vector intrinsics support (#2929)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
06abf8eeba
ggml : add view_src and view_offs to ggml_tensor for views (#2874)
|
%!s(int64=2) %!d(string=hai) anos |
|
xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
35feac6560
ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
f55538c3cc
metal : fix memory leak (#2762)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
103cfafc77
gguf : fix strings to not be null-terminated (#2839)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
d0cee0d36d
gguf : add 64-bit support (GGUF v2) (#2821)
|
%!s(int64=2) %!d(string=hai) anos |
|
Przemysław Pawełczyk
|
1591e2e590
ggml : detect SSSE3 (#2825)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
ef3f333d37
ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
%!s(int64=2) %!d(string=hai) anos |
