Johannes Gäßler 7f4d110f53 CUDA: fix FTZ in FA for Gemma 3 (llama/13991)

2025-06-10 12:40:33 +03:00

..

ggml-amx

…

ggml-blas

cmake : Fix broken CMake error messages (ggml/1252)

2025-06-01 15:14:44 +03:00

ggml-cann

CANN: Add SOC TYPE printing in cmake configuration (llama/13837)

2025-06-01 15:14:44 +03:00

ggml-cpu

cmake : Handle mixed-case 'Power' strings in POWER CPU detection (llama/13966)

2025-06-10 12:40:33 +03:00

ggml-cuda

CUDA: fix FTZ in FA for Gemma 3 (llama/13991)

2025-06-10 12:40:33 +03:00

ggml-hip

CUDA/HIP: Share the same unified memory allocation logic. (llama/12934)

2025-04-24 20:39:16 +03:00

ggml-kompute

…

ggml-metal

metal : use F32 accumulators in FA kernels (llama/13975)

2025-06-10 12:40:33 +03:00

ggml-musa

musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (llama/13647)

2025-05-27 18:03:00 +03:00

ggml-opencl

opencl: add backend_synchronize (llama/13939)

2025-06-10 12:40:33 +03:00

ggml-rpc

rpc : add rpc_msg_set_tensor_hash_req (llama/13353)

2025-05-13 13:59:21 +03:00

ggml-sycl

sycl: quantize and reorder the input to q8_1 when reorder is enabled (llama/13826)

2025-06-10 12:40:33 +03:00

ggml-vulkan

vulkan: fix warnings in perf logger querypool code (llama/13937)

2025-06-10 12:40:33 +03:00

CMakeLists.txt

Add in-build ggml::ggml ALIAS library (ggml/1260)

2025-06-10 12:40:33 +03:00

ggml-alloc.c

ggml: Don't assert fail when tensor data changes (llama/13222)

2025-05-07 15:39:32 +03:00

ggml-backend-impl.h

…

ggml-backend-reg.cpp

…

ggml-backend.cpp

sched : avoid changing cur_copy when a graph is already allocated (llama/13922)

2025-06-01 15:14:44 +03:00

ggml-common.h

musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc (llama/12611)

2025-03-31 14:56:53 +03:00

ggml-impl.h

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

2025-05-29 09:56:26 +03:00

ggml-opt.cpp

mnist: fix segmentation fault (ggml/1227)

2025-05-19 14:58:39 +03:00

ggml-quants.c

whisper: remove MSVC warnings pragmas (#3090)

2025-05-05 13:09:35 +02:00

ggml-quants.h

…

ggml-threading.cpp

…

ggml-threading.h

…

ggml.c

ggml : add ggml_repeat_4d (llama/13824)

2025-06-01 15:14:44 +03:00

ggml.cpp

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

2025-05-29 09:56:26 +03:00

gguf.cpp

gguf: fix failure on version == 0 (llama/13956)

2025-06-10 12:40:33 +03:00