| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-cann
|
938f608742
CANN: RoPE operator optimization (#10563)
|
1 year ago |
|
ggml-cpu
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 year ago |
|
ggml-cuda
|
e9e661bd59
CUDA: remove unnecessary warp reduce in FA (ggml/1032)
|
1 year ago |
|
ggml-hip
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-kompute
|
2025fa67e9
kompute : improve backend to pass test_backend_ops (#10542)
|
1 year ago |
|
ggml-metal
|
efb6ae9630
feat: add `GGML_UNARY_OP_ARGMAX` Metal kernel (ggml/1019)
|
1 year ago |
|
ggml-musa
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
1 year ago |
|
ggml-rpc
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-sycl
|
991f8aabee
SYCL: Fix and switch to GGML_LOG system instead of fprintf (#10579)
|
1 year ago |
|
ggml-vulkan
|
0533e7fb38
vulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536)
|
1 year ago |
|
CMakeLists.txt
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
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
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 year ago |
|
ggml-backend-reg.cpp
|
3420909dff
ggml : automatic selection of best CPU backend (#10606)
|
1 year ago |
|
ggml-backend.cpp
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 year ago |
|
ggml-common.h
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 year ago |
|
ggml-impl.h
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 year ago |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
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
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 year ago |
mahorozte
e9e661bd59
CUDA: remove unnecessary warp reduce in FA (ggml/1032)