 Kawrakow
|
49662cbed3
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
|
2 lat temu |
 Georgi Gerganov
|
18c2e1752c
ggml : fix vld1q_s8_x4 32-bit compat (#4828)
|
2 lat temu |
|
Kawrakow
|
dd5ae06405
SOTA 2-bit quants (#4773)
|
2 lat temu |
|
Georgi Gerganov
|
e39106c055
ggml : add ggml_vdotq_s32 alias (#4715)
|
2 lat temu |
|
Georgi Gerganov
|
951010fa53
ggml : fix dot product for ARM (#4630)
|
2 lat temu |
 FantasyGmm
|
a55876955b
cuda : fix jetson compile error (#4560)
|
2 lat temu |
 Richard Kiss
|
9494d7c477
english : use `typos` to fix comments and logs (#4354)
|
2 lat temu |
 Roger Meier
|
8e9361089d
build : support ppc64le build for make and CMake (#3963)
|
2 lat temu |
 Michael Potter
|
6bb4908a17
Fix MacOS Sonoma model quantization (#4052)
|
2 lat temu |
|
Georgi Gerganov
|
3d68f364f1
ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)
|
2 lat temu |
|
Georgi Gerganov
|
9a3b4f6c86
ggml : fix UNUSED macro (#3762)
|
2 lat temu |
 Andrew Godfrey
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 lat temu |
|
Georgi Gerganov
|
207b51900e
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
|
2 lat temu |
|
Georgi Gerganov
|
d69d777c02
ggml : quantization refactoring (#3833)
|
2 lat temu |
