| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-cann
|
92a391327e
[CANN]MUL_MAT optimization (#12382)
|
10 months ago |
|
ggml-cpu
|
eba92d64c3
cmake : fix PowerPC build (#12241)
|
10 months ago |
|
ggml-cuda
|
bb115d2bf7
musa: override warp_size of musa device to 32 (#12445)
|
10 months ago |
|
ggml-hip
|
becade5de7
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)
|
10 months ago |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 year ago |
|
ggml-metal
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 months ago |
|
ggml-musa
|
b1b132efcb
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)
|
10 months ago |
|
ggml-opencl
|
8acdacb3ea
opencl: use OpenCL C standard supported by the device (#12221)
|
10 months ago |
|
ggml-rpc
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 months ago |
|
ggml-sycl
|
35cae5ba05
SYCL: using graphs is configurable by environment variable and compile option (#12371)
|
10 months ago |
|
ggml-vulkan
|
fd123cfead
Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentation and driver issues (#12434)
|
10 months ago |
|
CMakeLists.txt
|
374101fd74
cmake : enable building llama.cpp using system libggml (#12321)
|
10 months ago |
|
ggml-alloc.c
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 months ago |
|
ggml-backend-impl.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 months ago |
|
ggml-backend-reg.cpp
|
ba7654380a
ggml-backend : fix backend search path (#12330)
|
10 months ago |
|
ggml-backend.cpp
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 months ago |
|
ggml-common.h
|
b9ab0a4d0b
CUDA: use arch list for compatibility check (#11775)
|
11 months ago |
|
ggml-impl.h
|
0b3863ff95
MUSA: support ARM64 and enable dp4a .etc (#11843)
|
11 months ago |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
1 year ago |
|
ggml-quants.c
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 months ago |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 year ago |
|
ggml.c
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 months ago |
|
gguf.cpp
|
4dd34ff831
cmake : add sanitizer flags for llama.cpp (#11279)
|
1 year ago |
R0CKSTAR
bb115d2bf7
musa: override warp_size of musa device to 32 (#12445)