| .. |
|
ggml-blas
|
rename optimize_graph to graph_optimize (llama/16082)
|
2025-09-20 13:46:39 +03:00 |
|
ggml-cann
|
CANN: Improve device ID handling and aclnnArange checks (llama/16752)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-cpu
|
Revert "ggml-cpu: detect correct cpu flags for arm64 (llama/16229) (#16239)" (llama/17084)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-cuda
|
CUDA: fix MMQ stream-k fixup ne1 indices (llama/17089)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-hexagon
|
ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (llama/16987)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-hip
|
HIP: fix AMDGPU_TARGETS, update documentation (llama/16803)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-metal
|
metal : initial Metal4 tensor API support (llama/16634)
|
2025-11-09 23:38:03 +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
|
opencl: support imrope (llama/16914)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-rpc
|
rpc : report actual free memory (llama/16616)
|
2025-10-22 12:58:11 +03:00 |
|
ggml-sycl
|
sycl: add CONCAT operator support (llama/16047)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-vulkan
|
vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm.comp (llama/16636)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-webgpu
|
ggml webgpu: faster matrix multiplication/matrix-vector multiplication (llama/17031)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-zdnn
|
zdnn: refactor codebase + add docs (llama/16178)
|
2025-09-29 15:18:09 +03:00 |
|
CMakeLists.txt
|
ggml: add s390x cpu-feats (llama/16774)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-alloc.c
|
ggml-alloc : make gallocr prefer chunks that allow memory reuse (llama/16788)
|
2025-11-09 23:38:03 +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
|
Add experimental ggml-hexagon backend for the Hexagon NPU (llama/16547)
|
2025-11-09 23:38:03 +02:00 |
|
ggml-backend.cpp
|
llama: print memory breakdown on exit (llama/15860)
|
2025-09-29 15:18:10 +03:00 |
|
ggml-common.h
|
llama : add gpt-oss (llama/15091)
|
2025-08-18 20:30:45 +03:00 |
|
ggml-impl.h
|
vulkan: Update topk_moe fusion to handle gpt's late softmax (llama/16656)
|
2025-11-09 23:38:03 +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 : 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: add ggml_can_fuse_subgraph (llama/16662)
|
2025-10-22 12:58:11 +03:00 |
|
ggml.cpp
|
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
2025-05-29 09:56:26 +03:00 |
|
gguf.cpp
|
ggml : prevent integer overflow in gguf tensor size calculation (llama/14595)
|
2025-07-12 19:23:56 +03:00 |
0caa32c772