 Neo Zhang Jianyu
|
2a358fb0c4
[SYCL] add check malloc result on device (#9346)
|
1 rok temu |
 luoyu-intel
|
1731d4238f
[SYCL] Add oneDNN primitive support (#9091)
|
1 rok temu |
 Meng, Hengyu
|
50addec9a5
[SYCL] fallback mmvq (#9088)
|
1 rok temu |
 zhentaoyu
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 rok temu |
|
zhentaoyu
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
1 rok temu |
|
Meng, Hengyu
|
0832de7236
[SYCL] add conv support (#8688)
|
1 rok temu |
 slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 rok temu |
|
Meng, Hengyu
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 rok temu |
 Chen Xi
|
b549a1bbef
[SYCL] fix the mul_mat_id ut issues (#8427)
|
1 rok temu |
 Alberto Cabrera Pérez
|
5b0b8d8cfb
sycl : Reenabled mmvq path for the SYCL Nvidia Backend (#8372)
|
1 rok temu |
 Ouadie EL FAROUKI
|
1f3e1b66e2
Enabled more data types for oneMKL gemm_batch (#8236)
|
1 rok temu |
|
luoyu-intel
|
a9554e20b6
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
|
1 rok temu |
|
Neo Zhang Jianyu
|
f09b7cb609
rm get_work_group_size() by local cache for performance (#8286)
|
1 rok temu |
|
luoyu-intel
|
d08c20edde
[SYCL] Fix the sub group size of Intel (#8106)
|
1 rok temu |
|
zhentaoyu
|
197fe6c1d7
[SYCL] Update SYCL-Rope op and Refactor (#8157)
|
1 rok temu |
 Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 rok temu |
