 Zhiyuan Li
|
3bcd40b3c5
Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)
|
1 year ago |
 Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
1 year ago |
 Ouadie EL FAROUKI
|
87421a23e8
[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705)
|
1 year ago |
|
Diego Devesa
|
c83ad6d01e
ggml-backend : add device and backend reg interfaces (#9707)
|
1 year ago |
 Akarshan Biswas
|
e62e9789cd
Revert "[SYCL] fallback mmvq (#9088)" (#9579)
|
1 year ago |
 Georgi Gerganov
|
d13edb17ed
ggml : fix builds (#0)
|
1 year ago |
 Johannes Gäßler
|
424c5d00a9
ggml/examples: add backend support for numerical optimization (ggml/949)
|
1 year ago |
|
Georgi Gerganov
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
1 year ago |
 Alberto Cabrera Pérez
|
51b6038636
sycl : update support conditions (#9394)
|
1 year ago |
 Neo Zhang Jianyu
|
2a358fb0c4
[SYCL] add check malloc result on device (#9346)
|
1 year ago |
 luoyu-intel
|
1731d4238f
[SYCL] Add oneDNN primitive support (#9091)
|
1 year ago |
 Meng, Hengyu
|
50addec9a5
[SYCL] fallback mmvq (#9088)
|
1 year ago |
 zhentaoyu
|
4f8d19ff17
[SYCL] Fix SYCL `im2col` and `convert` Overflow with Large Dims (#9052)
|
1 year ago |
|
zhentaoyu
|
c887d8b017
[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
|
1 year ago |
|
Meng, Hengyu
|
0832de7236
[SYCL] add conv support (#8688)
|
1 year ago |
|
slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 year ago |
|
Meng, Hengyu
|
16bdfa42ac
[SYCL] add concat through dim 1/2 (#8483)
|
1 year ago |
 Chen Xi
|
b549a1bbef
[SYCL] fix the mul_mat_id ut issues (#8427)
|
1 year ago |
|
Alberto Cabrera Pérez
|
5b0b8d8cfb
sycl : Reenabled mmvq path for the SYCL Nvidia Backend (#8372)
|
1 year ago |
|
Ouadie EL FAROUKI
|
1f3e1b66e2
Enabled more data types for oneMKL gemm_batch (#8236)
|
1 year ago |
|
luoyu-intel
|
a9554e20b6
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
|
1 year ago |
|
Neo Zhang Jianyu
|
f09b7cb609
rm get_work_group_size() by local cache for performance (#8286)
|
1 year ago |
|
luoyu-intel
|
d08c20edde
[SYCL] Fix the sub group size of Intel (#8106)
|
1 year ago |
|
zhentaoyu
|
197fe6c1d7
[SYCL] Update SYCL-Rope op and Refactor (#8157)
|
1 year ago |
|
Georgi Gerganov
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
