| .. |
|
ggml-amx
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-cann
|
605fa66c50
CANN: Fix SOC_TYPE compile bug (#10519)
|
1 year ago |
|
ggml-cpu
|
25669aa92c
ggml-cpu: cmake add arm64 cpu feature check for macos (#10487)
|
1 year ago |
|
ggml-cuda
|
3ad5451f3b
Add some minimal optimizations for CDNA (#10498)
|
1 year ago |
|
ggml-hip
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-kompute
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-metal
|
9e2301f4a4
metal : fix group_norm support condition (#0)
|
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
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-vulkan
|
c31ed2abfc
vulkan: define all quant data structures in types.comp (#10440)
|
1 year ago |
|
CMakeLists.txt
|
ab96610b1e
cmake : enable warnings in llama (#10474)
|
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
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-backend-reg.cpp
|
10bce0450f
llama : accept a list of devices to use to offload a model (#10497)
|
1 year ago |
|
ggml-backend.cpp
|
59b9172822
ggml/sched : do not skip views in pre-assignments
|
1 year ago |
|
ggml-common.h
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 year ago |
|
ggml-impl.h
|
9150f8fef9
Do not include arm_neon.h when compiling CUDA code (ggml/1028)
|
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
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
leo-pony
605fa66c50
CANN: Fix SOC_TYPE compile bug (#10519)