Эхлэл Бүгдийг харах Тусламж
Нэвтрэх
cturan
/
llama.cpp
-ын хуулбар https://github.com/cturan/llama.cpp
1
0
Салаа 0
Файлууд Асуудлууд 0 Мэдлэгийн сан
Мод: 0cf867160c
Салаанууд Тагууд
llama.cpp
/
ggml
/
src
/
ggml-sycl
Akarshan Biswas ec3bc8270b SYCL: remove XMX info from print devices (#11712) 1 жил өмнө
..
dpct 99487b57d4 SYCL: Introducing memory host pool (#11251) 1 жил өмнө
CMakeLists.txt 40c6d79fb5 SYCL : Move to compile time oneMKL interface backend selection for NVIDIA backend (#10584) 1 жил өмнө
backend.hpp f446c2cf6a SYCL: Add gated linear attention kernel (#11175) 1 жил өмнө
common.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
common.hpp 99487b57d4 SYCL: Introducing memory host pool (#11251) 1 жил өмнө
concat.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
concat.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
conv.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
conv.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
convert.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
convert.hpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 жил өмнө
dequantize.hpp 5639971466 Fixed dequant precision issues in Q4_1 and Q5_1 (#9711) 1 жил өмнө
dmmv.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
dmmv.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 жил өмнө
element_wise.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
element_wise.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
gemm.hpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
ggml-sycl.cpp ec3bc8270b SYCL: remove XMX info from print devices (#11712) 1 жил өмнө
gla.cpp f446c2cf6a SYCL: Add gated linear attention kernel (#11175) 1 жил өмнө
gla.hpp f446c2cf6a SYCL: Add gated linear attention kernel (#11175) 1 жил өмнө
im2col.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
im2col.hpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 жил өмнө
mmq.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
mmq.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 жил өмнө
mmvq.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
mmvq.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 жил өмнө
norm.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
norm.hpp d08c20edde [SYCL] Fix the sub group size of Intel (#8106) 1 жил өмнө
outprod.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
outprod.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
presets.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 жил өмнө
rope.cpp 83ed24a97b SYCL: Reduce most of the compiler warnings (#10748) 1 жил өмнө
rope.hpp 197fe6c1d7 [SYCL] Update SYCL-Rope op and Refactor (#8157) 1 жил өмнө
softmax.cpp 6e84b0ab8e SYCL : SOFTMAX F16 mask support and other fixes (#11261) 1 жил өмнө
softmax.hpp 6e84b0ab8e SYCL : SOFTMAX F16 mask support and other fixes (#11261) 1 жил өмнө
tsembd.cpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
tsembd.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө
vecdotq.hpp 5a54af4d4f sycl: Use syclcompat::dp4a (#10267) 1 жил өмнө
wkv6.cpp ee7136c6d1 llama: add support for QRWKV6 model architecture (#11001) 1 жил өмнө
wkv6.hpp c6860cc734 SYCL: Refactor ggml_sycl_compute_forward (#11121) 1 жил өмнө