| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
ggml-cann
|
7a395f67a7
CANN: Add support for async operator submission (#12864)
|
9 months ago |
|
ggml-cpu
|
13b0a04597
whisper: remove MSVC warnings pragmas (whisper/3090)
|
8 months ago |
|
ggml-cuda
|
7474e00b34
CUDA: fix crash with partial offloading of MoE (#13439)
|
8 months ago |
|
ggml-hip
|
84778e9770
CUDA/HIP: Share the same unified memory allocation logic. (#12934)
|
9 months ago |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 year ago |
|
ggml-metal
|
611aa914ef
metal : optimize MoE for large batches (#13388)
|
8 months ago |
|
ggml-musa
|
b1b132efcb
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)
|
10 months ago |
|
ggml-opencl
|
12b17501e6
opencl: fix incorrect local_size index in profiling log (#12868)
|
9 months ago |
|
ggml-rpc
|
b486ba05bf
rpc : add rpc_msg_set_tensor_hash_req (#13353)
|
8 months ago |
|
ggml-sycl
|
17512a94d6
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs (#12858)
|
8 months ago |
|
ggml-vulkan
|
dc1d2adfc0
vulkan: scalar flash attention implementation (#13324)
|
8 months ago |
|
CMakeLists.txt
|
bba9d945c1
cmake : removed stdc++fs (whisper/3097)
|
8 months ago |
|
ggml-alloc.c
|
f057808ffa
ggml: Don't assert fail when tensor data changes (#13222)
|
8 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
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 months ago |
|
ggml-common.h
|
492d7f1ff7
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (#12611)
|
9 months ago |
|
ggml-impl.h
|
cb79c2e7fa
ggml: don't include arm_neon.h when using CUDA 12 with ARM Neon (ggml/1187)
|
9 months ago |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
1 year ago |
|
ggml-quants.c
|
13b0a04597
whisper: remove MSVC warnings pragmas (whisper/3090)
|
8 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
|
611aa914ef
metal : optimize MoE for large batches (#13388)
|
8 months ago |
|
gguf.cpp
|
a6f32f0b34
Fix clang warning in gguf_check_reserved_keys (#12686)
|
9 months ago |
Johannes Gäßler
7474e00b34
CUDA: fix crash with partial offloading of MoE (#13439)