| .. |
|
ggml-amx
|
5d9e59979c
ggml : adapt AMX to tensor->grad removal (#0)
|
1 year ago |
|
ggml-blas
|
3ee6382d48
cuda : fix CUDA_FLAGS not being applied (#10403)
|
1 year ago |
|
ggml-cann
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-cpu
|
42ae10bbcd
add cmake rvv support (#10411)
|
1 year ago |
|
ggml-cuda
|
3ee6382d48
cuda : fix CUDA_FLAGS not being applied (#10403)
|
1 year ago |
|
ggml-hip
|
c3ea58aca4
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)
|
1 year ago |
|
ggml-kompute
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-metal
|
611fabd792
metal : fox offset integer overflows in im2col (ggml/1015)
|
1 year ago |
|
ggml-musa
|
c3ea58aca4
CUDA: remove DMMV, consolidate F16 mult mat vec (#10318)
|
1 year ago |
|
ggml-rpc
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-sycl
|
2a1507c162
sycl : Add option to set the SYCL architecture for all targets (#10266)
|
1 year ago |
|
ggml-vulkan
|
1bacb9f625
vulkan: further optimize mul_mat_vec using larger loads (#10387)
|
1 year ago |
|
CMakeLists.txt
|
2a11b6b094
Add required ggml-base and backend libs to cmake pkg (#10407)
|
1 year ago |
|
ggml-aarch64.c
|
1e58ee1318
ggml : optimize Q4_0 into Q4_0_X_Y repack (#10324)
|
1 year ago |
|
ggml-aarch64.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-alloc.c
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
1 year ago |
|
ggml-backend-impl.h
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
1 year ago |
|
ggml-backend-reg.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-backend.cpp
|
be5caccef9
llama : only use default buffer types for the KV cache (#10358)
|
1 year ago |
|
ggml-common.h
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
ggml-impl.h
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
1 year ago |
|
ggml-opt.cpp
|
24203e9dd7
ggml : inttypes.h -> cinttypes (#0)
|
1 year ago |
|
ggml-quants.c
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year 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
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml.c
|
68fcb4759c
ggml : fix compile warnings (#0)
|
1 year ago |
Jeff Bolz
1bacb9f625
vulkan: further optimize mul_mat_vec using larger loads (#10387)