Releases: ggml-org/llama.cpp
Releases · ggml-org/llama.cpp
b4847
metal : simplify kernel arguments using a struct (#3229) (#12194) * metal : refactor im2col parameters into a struct * metal: Change im2col offset types from int32_t to uint64_t to support larger memory offsets * metal : refactor sum_rows parameters into a struct * metal : refactor soft_max parameters into a struct * metal : refactor diag_mask_inf parameters into a struct * metal : refactor ssm_conv parameters into a struct * metal : refactor ssm_scan parameters into a struct * metal : refactor get_rows parameters into a struct * metal : refactor group_norm parameters into a struct * metal : refactor conv_transpose_1d parameters into a struct * metal : refactor upscale parameters into a struct * metal : refactor pad parameters into a struct * metal : refactor pad_reflect_1d parameters into a struct * metal : refactor arange parameters into a struct * metal : refactor timestep_embedding parameters into a struct * metal : refactor argsort parameters into a struct * metal : refactor leaky_relu parameters into a struct * metal : refactor pool_2d parameters into a struct * metal : fix trailing whitespace --------- Co-authored-by: alexju <[email protected]>
b4846
HIP: fix rocWMMA build flags under Windows (#12230)
b4837
HIP/CUDA: set the paramerter value in maintain_cuda_graph instead of …
b4836
android : fix KV cache log message condition (#12212)
b4835
opencl : fix buffer alignment (#12197) Fix the following error: ``` ggml-alloc.c:99: not enough space in the buffer ggml_tallocr_alloc: not enough space in the buffer to allocate blk.17.ffn_down.weight (needed 27525120, available 27521024) ``` which occurs when `ggml_backend_opencl_context::alignment` is larger than `cl_ptr_base` (hard-coded to `0x1000`). Also, fix `ggml_backend_opencl_context::alignment` was set to `CL_DEVICE_MEM_BASE_ADDR_ALIGN` which was treated as bytes but the value is reported in bits.
b4834
opencl : fix `ulong` kernel args were set from `int` variables (#12174) ... which left garbage bits in the upper half of the kernel args. This caused segmentation faults when running PoCL.
b4833
opencl : fix profile-related errors (#12095) Co-authored-by: ubuntu <[email protected]>
b4832
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (#12…
b4831
SYCL: Disable f16 Unary OPs as not supported by the kernels (#12201)
b4830
ggml : fix GGMLMetalClass ODR (#12200) -- it might happen if ggml is loaded from 2 separate libraries since each one of them will expose the class. This is more of a guard since we want to use only Metal as embedded library and don't care about the other case.