Home Esplora Aiuto
Accedi
cturan
/
llama.cpp
mirror da https://github.com/cturan/llama.cpp
1
0
Forka 0
File Problemi 0 Wiki
Albero (Tree): 8c32d9d96d
Rami (Branch) Tag
llama.cpp
/
ggml
/
src
Neo Zhang 7d2add51d8 sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566) 2 mesi fa
..
ggml-blas 4d3d455d3c sync : whisper.cpp (ggml/1359) 4 mesi fa
ggml-cann eeb5605de2 CANN: Add MROPE and IMROPE support (#17401) 2 mesi fa
ggml-cpu f698a79c63 ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567) 2 mesi fa
ggml-cuda c6f7a423c8 [MUSA] enable fp16/fast_fp16/bf16_mma on PH1 (#17551) 2 mesi fa
ggml-hexagon 923ae3c619 hexagon: add support for ROPE_NEOX (#17458) 2 mesi fa
ggml-hip 80d28f104c HIP: fix AMDGPU_TARGETS, update documentation (#16803) 3 mesi fa
ggml-metal 583cb83416 ggml : add ggml_top_k (#17365) 2 mesi fa
ggml-musa 11f0af5504 CUDA: faster tile FA, add oob checks, more HSs (#16492) 3 mesi fa
ggml-opencl 7cba58bbea opencl: add sqr, sqrt, mean and ssm_conv (#17476) 2 mesi fa
ggml-rpc 15d2b46b4d rpc : cache and reuse compute graphs (#15405) 2 mesi fa
ggml-sycl 7d2add51d8 sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566) 2 mesi fa
ggml-vulkan 47a268ea50 Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900) 2 mesi fa
ggml-webgpu 647b960bd8 ggml webgpu: faster matrix multiplication/matrix-vector multiplication (#17031) 2 mesi fa
ggml-zdnn 264f1b5187 zdnn: refactor codebase + add docs (#16178) 4 mesi fa
CMakeLists.txt e072b2052e ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) 2 mesi fa
ggml-alloc.c e072b2052e ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) 2 mesi fa
ggml-backend-impl.h 898acba681 rpc : add support for multiple devices (#16276) 3 mesi fa
ggml-backend-reg.cpp 63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 3 mesi fa
ggml-backend.cpp e072b2052e ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in ggml_backend_sched (#17276) 2 mesi fa
ggml-common.h fd1234cb46 llama : add gpt-oss (#15091) 5 mesi fa
ggml-impl.h 389ac78b26 ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063) 2 mesi fa
ggml-opt.cpp 5cdb27e091 finetune: SGD optimizer, more CLI args (#13873) 5 mesi fa
ggml-quants.c f6b4af3d04 ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928) 4 mesi fa
ggml-quants.h fd1234cb46 llama : add gpt-oss (#15091) 5 mesi fa
ggml-threading.cpp ae8de6d50a ggml : build backends as libraries (#10256) 1 anno fa
ggml-threading.h cb13ef85a4 remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 1 anno fa
ggml.c 583cb83416 ggml : add ggml_top_k (#17365) 2 mesi fa
ggml.cpp fedf034a98 ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 8 mesi fa
gguf.cpp a81283820a gguf: gguf_writer refactor (#15691) 4 mesi fa