whisper.cpp / ggml /src /ggml-sycl.cpp

Commit History

Add oneDNN primitive support (llama/9091)
b4d8c3e

KevinLy commited on

fallback mmvq (llama/9088)
4b1fda0

hengyu Alberto Cabrera Pérez commited on

Fix SYCL `im2col` and `convert` Overflow with Large Dims (llama/9052)
5f43886

zhentaoyu commited on

Add `TIMESTEP_EMBEDDING` OP (llama/8707)
52eea23

zhentaoyu commited on

add conv support (llama/8688)
f0d6f5c

hengyu commited on

ggml : reduce hash table reset cost (llama/8698)
9808fbf

slaren commited on

add concat through dim 1/2 (llama/8483)
acf23d9

hengyu commited on

fix the mul_mat_id ut issues (llama/8427)
374488a

ClarkChin hengyu Chen Xi commited on

sycl : Reenabled mmvq path for the SYCL Nvidia Backend (llama/8372)
b969571

Alberto Cabrera Pérez commited on

Enabled more data types for oneMKL gemm_batch (llama/8236)
08501f8

Ouadie EL FAROUKI commited on

Fix WARP_SIZE=16 bug of Intel GPU (llama/8266)
1ce11e2

KevinLy commited on

rm get_work_group_size() by local cache for performance (llama/8286)
08fd758

Neo Zhang Jianyu arthw commited on

Fix the sub group size of Intel (llama/8106)
2dd429e

KevinLy commited on

Update SYCL-Rope op and Refactor (llama/8157)
06acee2

zhentaoyu commited on

whisper : reorganize source code + improve CMake (#2256)
f75c2e3
unverified

ggerganov commited on