| .. |
|
ggml-blas
|
rename optimize_graph to graph_optimize (llama/16082)
|
2025-09-20 13:46:39 +03:00 |
|
ggml-cann
|
CANN: add support for partial RoPE and Vision mode (llama/17543)
|
2025-12-12 17:53:22 +02:00 |
|
ggml-cpu
|
Fix race conditions in threadpool when dealing with dynamic/frequent n_threads changes (llama/17748)
|
2025-12-12 17:53:24 +02:00 |
|
ggml-cuda
|
cuda : add missing support check for xielu (llama/17895)
|
2025-12-12 17:53:23 +02:00 |
|
ggml-hexagon
|
ggml-hexagon: fix `rope` failure at `test-backend-ops` (llama/17565)
|
2025-12-12 17:53:24 +02:00 |
|
ggml-hip
|
HIP: fix AMDGPU_TARGETS, update documentation (llama/16803)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-metal
|
metal: SSM kernel improvements (llama/17876)
|
2025-12-12 17:53:23 +02:00 |
|
ggml-musa
|
CUDA: faster tile FA, add oob checks, more HSs (llama/16492)
|
2025-10-15 09:29:17 +03:00 |
|
ggml-opencl
|
ggml : add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) (llama/16985)
|
2025-12-12 17:53:20 +02:00 |
|
ggml-rpc
|
ggml : improve error handling for search path existence checks (llama/17653)
|
2025-12-12 17:53:20 +02:00 |
|
ggml-sycl
|
fix softmax for iGPU (llama/17838)
|
2025-12-12 17:53:23 +02:00 |
|
ggml-vulkan
|
Vulkan: improve mul_mat_vec_iq1_m (llama/16907)
|
2025-12-12 17:53:21 +02:00 |
|
ggml-webgpu
|
ggml webgpu: unary op suppport, code refactoring, ops support (llama/17764)
|
2025-12-12 17:53:18 +02:00 |
|
ggml-zdnn
|
zdnn: refactor codebase + add docs (llama/16178)
|
2025-09-29 15:18:09 +03:00 |
|
ggml-zendnn
|
ggml-zendnn : add ZenDNN backend for AMD CPUs (llama/17690)
|
2025-12-12 17:53:21 +02:00 |
|
CMakeLists.txt
|
ggml-zendnn : add ZenDNN backend for AMD CPUs (llama/17690)
|
2025-12-12 17:53:21 +02:00 |
|
ggml-alloc.c
|
ggml-alloc : fix reuse-parent logic for misaligned sizes (llama/17884)
|
2025-12-12 17:53:24 +02:00 |
|
ggml-backend-impl.h
|
rpc : add support for multiple devices (llama/16276)
|
2025-10-12 11:16:23 +03:00 |
|
ggml-backend-reg.cpp
|
ggml-zendnn : add ZenDNN backend for AMD CPUs (llama/17690)
|
2025-12-12 17:53:21 +02:00 |
|
ggml-backend.cpp
|
ggml : remove redundant n_copies check when setting input/output (llama/17612)
|
2025-12-12 17:53:15 +02:00 |
|
ggml-common.h
|
llama : add gpt-oss (llama/15091)
|
2025-08-18 20:30:45 +03:00 |
|
ggml-impl.h
|
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (llama/17063)
|
2025-11-17 21:05:46 +02:00 |
|
ggml-opt.cpp
|
finetune: SGD optimizer, more CLI args (llama/13873)
|
2025-08-18 20:30:45 +03:00 |
|
ggml-quants.c
|
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (llama/15928)
|
2025-09-29 15:18:09 +03:00 |
|
ggml-quants.h
|
llama : add gpt-oss (llama/15091)
|
2025-08-18 20:30:45 +03:00 |
|
ggml-threading.cpp
|
…
|
|
|
ggml-threading.h
|
…
|
|
|
ggml.c
|
ggml : remove GGML_KQ_MASK_PAD constant (llama/17910)
|
2025-12-12 17:53:24 +02:00 |
|
ggml.cpp
|
…
|
|
|
gguf.cpp
|
ggml : prevent integer overflow in gguf tensor size calculation (llama/14595)
|
2025-07-12 19:23:56 +03:00 |
1da1a6865c