 Aaron Teo
|
046d5fd44e
llama: use host memory if device reports 0 memory (#18587)
|
3 هفته پیش |
 shaofeiqi
|
568371a726
opencl: add FILL op support (#18682)
|
3 هفته پیش |
 lhez
|
08566977a7
opencl: allow resizing transpose buffers (#18384)
|
1 ماه پیش |
|
lhez
|
eb492bf43f
opencl: unpack q4_0 for adreno in get_tensor (#18278)
|
1 ماه پیش |
 Phylliida Dev
|
09c7c50e64
ggml : add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) (#16985)
|
1 ماه پیش |
 Tarek Dakhran
|
2ba719519d
model: LFM2-VL fixes (#17577)
|
2 ماه پیش |
|
lhez
|
7cba58bbea
opencl: add sqr, sqrt, mean and ssm_conv (#17476)
|
2 ماه پیش |
|
lhez
|
8e9ddba610
opencl: refine condition for kqv mm (#17392)
|
2 ماه پیش |
|
lhez
|
52e5d421f1
opencl: fix rms_norm_mul (#17250)
|
2 ماه پیش |
|
shaofeiqi
|
4db5641210
opencl: add kernel to handle mat mul in attention to improve encoding speed (#17181)
|
2 ماه پیش |
|
lhez
|
ece0f5c177
opencl: add fastdiv and use it in set_rows, ported from cuda (#17090)
|
2 ماه پیش |
 Acly
|
1032256ec9
cuda/vulkan : bicubic interpolation (#17022)
|
2 ماه پیش |
|
lhez
|
c5023daf60
opencl: support imrope (#16914)
|
2 ماه پیش |
|
Acly
|
10640e31aa
ggml : fix interpolate with align-corners and ne=1 (#16700)
|
3 ماه پیش |
|
lhez
|
6ea37f5739
opencl: fix warnings and clean up profiling (#16688)
|
3 ماه پیش |
 Shawn Gu
|
81387858f1
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602)
|
3 ماه پیش |
|
lhez
|
0cb7a0683b
opencl: add q8_0 mm support (#16469)
|
3 ماه پیش |
 Aman Gupta
|
120bf7046d
CUDA + openCL: fix bug in accessing rms_norm->src while doing fusion (#16577)
|
3 ماه پیش |
|
lhez
|
5016b72862
opencl: fix build targeting CL 2 (#16554)
|
3 ماه پیش |
|
lhez
|
7c156df414
opencl: support pad_ext (#15888)
|
4 ماه پیش |
|
lhez
|
d1c84a662d
opencl: support ne3 in get_rows (#15866)
|
4 ماه پیش |
 Sigbjørn Skjæret
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 ماه پیش |
|
lhez
|
51f5a45fbe
opencl: fix concat crash on win arm64 with Adreno (#15944)
|
4 ماه پیش |
|
lhez
|
c4510dc937
opencl: initial `q8_0` mv support (#15732)
|
4 ماه پیش |
|
Shawn Gu
|
3edd87cd05
opencl: optimize mxfp4 kernels (#16037)
|
4 ماه پیش |
 Jeff Bolz
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 ماه پیش |
|
Jeff Bolz
|
e68aa10d8f
vulkan: sort graph to allow more parallel execution (#15850)
|
4 ماه پیش |
 leejet
|
0a1b3982cd
ggml: add ops for WAN video model (cuda && cpu) (#15669)
|
4 ماه پیش |
 rmatif
|
820bc98531
opencl: add hs=40 to FA (#15758)
|
4 ماه پیش |
|
rmatif
|
97669e4073
opencl: add attn sinks support for FA kernels (#15706)
|
5 ماه پیش |
