bandoti
|
fef0cbeadf
cleanup: fix compile warnings associated with gnu_printf (#11811)
|
11 сар өмнө |
Johannes Gäßler
|
864a0b67a6
CUDA: use mma PTX instructions for FlashAttention (#11583)
|
11 сар өмнө |
Johannes Gäßler
|
9c8dcefe17
CUDA: backwards pass for misc. ops, add tests (#11257)
|
1 жил өмнө |
Johannes Gäßler
|
432df2d5f9
RoPE: fix back, CUDA support for back + noncont. (#11240)
|
1 жил өмнө |
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 жил өмнө |
Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 жил өмнө |
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 жил өмнө |
HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 жил өмнө |
Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 жил өмнө |
PAB
|
c2082d93a8
ggml : add `GGML_PAD_REFLECT_1D` operation (ggml/1034)
|
1 жил өмнө |
Shupei Fan
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 жил өмнө |
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 жил өмнө |
Johannes Gäßler
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
1 жил өмнө |
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 жил өмнө |
Georgi Gerganov
|
841f27abdb
metal : optimize FA kernels (#10171)
|
1 жил өмнө |
Zhiyuan Li
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 жил өмнө |
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 жил өмнө |
Diego Devesa
|
a6744e43e8
llama : add simple-chat example (#10124)
|
1 жил өмнө |
Georgi Gerganov
|
1804adb0cf
ggml : remove ggml_scratch (#10121)
|
1 жил өмнө |
Georgi Gerganov
|
f221d56220
ggml : alloc ggml_contexts on the heap (whisper/2525)
|
1 жил өмнө |
Ma Mingfei
|
60ce97c9d8
add amx kernel for gemm (#8998)
|
1 жил өмнө |
Diego Devesa
|
dca1d4b58a
ggml : fix BLAS with unsupported types (#9775)
|
1 жил өмнө |
Johannes Gäßler
|
fabdc3bda3
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
|
1 жил өмнө |
bandoti
|
d6fe7abf04
ggml: unify backend logging mechanism (#9709)
|
1 жил өмнө |
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 жил өмнө |
Johannes Gäßler
|
e98c1c188e
test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
|
1 жил өмнө |
Johannes Gäßler
|
7254cdf7e8
ggml: fix gradient allocation logic (ggml/966)
|
1 жил өмнө |
Georgi Gerganov
|
6084bfb261
ggml : fix GGML_MAX_N_THREADS + improve formatting (ggml/969)
|
1 жил өмнө |
Dan Johansson
|
6a0f779484
ggml : add run-time detection of neon, i8mm and sve (#9331)
|
1 жил өмнө |
Georgi Gerganov
|
c038931615
examples : adapt to ggml.h changes (ggml/0)
|
1 жил өмнө |