| .. |
|
ggml-amx
|
ggml : adapt AMX to tensor->grad removal (llama/0)
|
2024-11-20 21:00:08 +02:00 |
|
ggml-blas
|
ggml : add support for dynamic loading of backends (llama/10469)
|
2024-12-08 20:14:35 +02:00 |
|
ggml-cann
|
MUL_MAT optimization (llama/12382)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-cpu
|
cmake: Enable specifying exact PowerPC CPU architecture (ggml/1138)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-cuda
|
CUDA/HIP: Fix fattn-vec-* when device warp size is not 32 (llama/12315)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-hip
|
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (llama/12032)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-kompute
|
llama : add Qwen2VL support + multimodal RoPE (llama/10361)
|
2024-12-18 12:52:16 +02:00 |
|
ggml-metal
|
metal : Cache the Metal library at the device context level (llama/12265)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-musa
|
musa: support new arch mp_31 and update doc (llama/12296)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-opencl
|
opencl: use OpenCL C standard supported by the device (llama/12221)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-rpc
|
ggml : upgrade init_tensor API to return a ggml_status (llama/11854)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-sycl
|
sycl : variable sg_size support for mmvq kernels (llama/12336)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-vulkan
|
vulkan: fix bug in coopmat1 mul_mat_id (llama/12316)
|
2025-03-27 11:06:03 +02:00 |
|
CMakeLists.txt
|
cmake : fix undefined reference errors for std::filesystem in ggml (#12092) (llama/12094)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-alloc.c
|
ggml : upgrade init_tensor API to return a ggml_status (llama/11854)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-backend-impl.h
|
ggml : upgrade init_tensor API to return a ggml_status (llama/11854)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-backend-reg.cpp
|
ggml-backend : fix backend search path (llama/12330)
|
2025-03-27 11:06:03 +02:00 |
|
ggml-backend.cpp
|
ggml : portability fixes for VS 2017 (llama/12150)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-common.h
|
CUDA: use arch list for compatibility check (llama/11775)
|
2025-02-27 08:55:36 +02:00 |
|
ggml-impl.h
|
MUSA: support ARM64 and enable dp4a .etc (llama/11843)
|
2025-02-27 08:55:36 +02:00 |
|
ggml-opt.cpp
|
ggml-opt: fix data corruption (ggml/1022)
|
2024-12-08 20:14:35 +02:00 |
|
ggml-quants.c
|
ggml : portability fixes for VS 2017 (llama/12150)
|
2025-03-08 15:13:01 +02:00 |
|
ggml-quants.h
|
ggml : build backends as libraries (llama/10256)
|
2024-11-20 21:00:08 +02:00 |
|
ggml-threading.cpp
|
ggml : build backends as libraries (llama/10256)
|
2024-11-20 21:00:08 +02:00 |
|
ggml-threading.h
|
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)
|
2024-12-18 12:52:16 +02:00 |
|
ggml.c
|
ggml : ggml_compute_forward_concat() for arbitrary tensor type (ggml/1118)
|
2025-03-08 15:13:01 +02:00 |
|
gguf.cpp
|
cmake : add sanitizer flags for llama.cpp (llama/11279)
|
2025-02-03 22:00:57 +02:00 |
