happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src
History
hipudding 9961d244f2
CANN: Resolve soft_max precision issue (#15730) 
Previously, the slope tensor was set to fp16 to improve efficiency.
While this worked correctly in FA, it caused precision issues in soft_max.
This change applies different data types for different operators
to balance both accuracy and performance.
 		2025-09-02 17:12:37 +08:00
..
ggml-blas ggml : fix field name when new ggml_backend (#14944) 2025-08-08 14:37:22 +02:00
ggml-cann CANN: Resolve soft_max precision issue (#15730) 2025-09-02 17:12:37 +08:00
ggml-cpu ggml: SVE support for exponential functions (#15145) 2025-09-01 20:13:49 +02:00
ggml-cuda CUDA: fix build error from ambiguous __half conversions in conv2d (#15690) 2025-09-01 06:55:06 +05:30
ggml-hip HIP: bump requirement to rocm 6.1 (#15296) 2025-08-13 20:44:30 +02:00
ggml-metal metal : fix checks for available FA kernels (#15700) 2025-08-31 19:43:30 +03:00
ggml-musa CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433) 2025-08-20 16:58:49 +02:00
ggml-opencl opencl: add attn sinks support for FA kernels (#15706) 2025-09-01 23:26:53 -07:00
ggml-rpc ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (#15188) 2025-08-13 08:54:30 +03:00
ggml-sycl SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (#15592) 2025-08-27 00:27:49 +05:30
ggml-vulkan vulkan: Fix macro parameter order for f32 matmul shaders (#15716) 2025-09-02 14:37:01 +08:00
ggml-webgpu ggml : WebGPU add TRANSPOSE and RESHAPE to supported ops (#15695) 2025-09-01 14:28:49 +02:00
ggml-zdnn ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00
CMakeLists.txt ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00
ggml-alloc.c llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
ggml-backend-impl.h ggml : upgrade init_tensor API to return a ggml_status (#11854) 2025-02-28 14:41:47 +01:00
ggml-backend-reg.cpp ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00
ggml-backend.cpp ggml-backend: raise GGML_MAX_SPLIT_INPUTS (#15722) 2025-09-01 16:14:55 -07:00
ggml-common.h llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
ggml-impl.h llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
ggml-opt.cpp finetune: SGD optimizer, more CLI args (#13873) 2025-08-14 12:03:57 +02:00
ggml-quants.c ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (#15379) 2025-08-18 09:23:56 +02:00
ggml-quants.h llama : add gpt-oss (#15091) 2025-08-05 22:10:36 +03:00
ggml-threading.cpp ggml : build backends as libraries (#10256) 2024-11-14 18:04:35 +01:00
ggml-threading.h remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
ggml.c ggml: add `conv3d` op (#15182) 2025-08-22 15:33:15 +02:00
ggml.cpp ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 2025-06-01 13:43:57 +03:00
gguf.cpp ggml : prevent integer overflow in gguf tensor size calculation (#14595) 2025-07-09 14:33:53 +02:00