| .. |
|
dpct
|
5a54af4d4f
sycl: Use syclcompat::dp4a (#10267)
|
1 year ago |
|
CMakeLists.txt
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
backend.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
common.cpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
common.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
concat.cpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
concat.hpp
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 year ago |
|
conv.cpp
|
0832de7236
[SYCL] add conv support (#8688)
|
1 year ago |
|
conv.hpp
|
0832de7236
[SYCL] add conv support (#8688)
|
1 year ago |
|
convert.cpp
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 year ago |
|
convert.hpp
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 year ago |
|
dequantize.hpp
|
5639971466
Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)
|
1 year ago |
|
dmmv.cpp
|
5910ea9427
[SYCL] Fix DMMV dequantization (#9279)
|
1 year ago |
|
dmmv.hpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
element_wise.cpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
element_wise.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
gemm.hpp
|
1731d4238f
[SYCL] Add oneDNN primitive support (#9091)
|
1 year ago |
|
ggml-sycl.cpp
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
|
im2col.cpp
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 year ago |
|
im2col.hpp
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 year ago |
|
mmq.cpp
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 year ago |
|
mmq.hpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
mmvq.cpp
|
1db8c84fc6
fix mul_mat_vec_q and *_vec_q error (#9939)
|
1 year ago |
|
mmvq.hpp
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
norm.cpp
|
2e82ffa4af
sycl : Fixes to broken builds and test-backend-ops (#10257)
|
1 year ago |
|
norm.hpp
|
d08c20edde
[SYCL] Fix the sub group size of Intel (#8106)
|
1 year ago |
|
outprod.cpp
|
2e82ffa4af
sycl : Fixes to broken builds and test-backend-ops (#10257)
|
1 year ago |
|
outprod.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
presets.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
rope.cpp
|
06943a69f6
ggml : move rope type enum to ggml.h (#8949)
|
1 year ago |
|
rope.hpp
|
197fe6c1d7
[SYCL] Update SYCL-Rope op and Refactor (#8157)
|
1 year ago |
|
softmax.cpp
|
063d99ad11
[SYCL] fix scratch size of softmax (#8642)
|
1 year ago |
|
softmax.hpp
|
a9554e20b6
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
|
1 year ago |
|
tsembd.cpp
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
1 year ago |
|
tsembd.hpp
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
1 year ago |
|
vecdotq.hpp
|
5a54af4d4f
sycl: Use syclcompat::dp4a (#10267)
|
1 year ago |
|
wkv6.cpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
|
wkv6.hpp
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
Diego Devesa
5931c1f233
ggml : add support for dynamic loading of backends (#10469)