Startsida Utforska Hjälp
Logga in
cturan
/
llama.cpp
spegling av https://github.com/cturan/llama.cpp
1
0
Fork 0
Filer Ärenden 0 Wiki
Träd: a2c6fd747c
Grenar Taggar
llama.cpp
/
ggml
/
src
/
ggml-sycl
Zhiyuan Li 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
..
dpct 0478174d59 [SYCL] Updated SYCL device filtering (#8901) 1 år sedan
backend.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
common.cpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
common.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
concat.cpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
concat.hpp 16bdfa42ac [SYCL] add concat through dim 1/2 (#8483) 1 år sedan
conv.cpp 0832de7236 [SYCL] add conv support (#8688) 1 år sedan
conv.hpp 0832de7236 [SYCL] add conv support (#8688) 1 år sedan
convert.cpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 år sedan
convert.hpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 år sedan
dequantize.hpp 5639971466 Fixed dequant precision issues in Q4_1 and Q5_1 (#9711) 1 år sedan
dmmv.cpp 5910ea9427 [SYCL] Fix DMMV dequantization (#9279) 1 år sedan
dmmv.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 år sedan
element_wise.cpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
element_wise.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
gemm.hpp 1731d4238f [SYCL] Add oneDNN primitive support (#9091) 1 år sedan
im2col.cpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 år sedan
im2col.hpp 4f8d19ff17 [SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052) 1 år sedan
mmq.cpp 2b1f616b20 ggml : reduce hash table reset cost (#8698) 1 år sedan
mmq.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 år sedan
mmvq.cpp 1db8c84fc6 fix mul_mat_vec_q and *_vec_q error (#9939) 1 år sedan
mmvq.hpp f3f65429c4 llama : reorganize source code + improve CMake (#8006) 1 år sedan
norm.cpp 2d5dd7bb3f ggml : add epsilon as a parameter for group_norm (#8818) 1 år sedan
norm.hpp d08c20edde [SYCL] Fix the sub group size of Intel (#8106) 1 år sedan
outprod.cpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
outprod.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
presets.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
rope.cpp 06943a69f6 ggml : move rope type enum to ggml.h (#8949) 1 år sedan
rope.hpp 197fe6c1d7 [SYCL] Update SYCL-Rope op and Refactor (#8157) 1 år sedan
softmax.cpp 063d99ad11 [SYCL] fix scratch size of softmax (#8642) 1 år sedan
softmax.hpp a9554e20b6 [SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266) 1 år sedan
tsembd.cpp c887d8b017 [SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707) 1 år sedan
tsembd.hpp c887d8b017 [SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707) 1 år sedan
vecdotq.hpp cb5fad4c6c CUDA: refactor and optimize IQ MMVQ (#8215) 1 år sedan
wkv6.cpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan
wkv6.hpp 3bcd40b3c5 Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133) 1 år sedan