 lhez
|
f0d46ef157
opencl: remove unnecessary assert for `add` (#13257)
|
8 months ago |
 kimminsu
|
12b17501e6
opencl: fix incorrect local_size index in profiling log (#12868)
|
9 months ago |
|
lhez
|
80f19b4186
opencl: split `ggml-opencl.cl` into multiple files and cleanup (#12886)
|
9 months ago |
|
lhez
|
82974011f3
opencl: better identify Adreno GPU (#12760)
|
10 months ago |
|
lhez
|
97a20c012b
opencl: use `max_alloc_size` in backend ctx instead of querying again (#12705)
|
10 months ago |
 Junil Kim
|
f423981ac8
opencl : fix memory allocation size (#12649)
|
10 months ago |
|
lhez
|
5dec47dcd4
opencl: add multi and vision rope, `gelu_quick` and `im2col` (#12600)
|
10 months ago |
|
lhez
|
d84635b1b0
opencl: improve profiling (#12442)
|
10 months ago |
 Henry Linjamäki
|
8acdacb3ea
opencl: use OpenCL C standard supported by the device (#12221)
|
10 months ago |
|
lhez
|
d76a86d967
opencl: Noncontiguous `norm`, `rms_norm`, disable `fp16` for some ops (#12217)
|
11 months ago |
 Henry Linjamäki
|
94bb63e4f0
opencl : fix buffer alignment (#12197)
|
11 months ago |
|
Henry Linjamäki
|
f79243992c
opencl : fix `ulong` kernel args were set from `int` variables (#12174)
|
11 months ago |
 simon886212
|
ed4ce0dda2
opencl : fix profile-related errors (#12095)
|
11 months ago |
 William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
11 months ago |
|
lhez
|
34a846b584
opencl: fix for small models (#11950)
|
11 months ago |
|
lhez
|
300907b211
opencl: Fix rope and softmax (#11833)
|
11 months ago |
 Peter
|
6e1531aca5
common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON (#11013)
|
1 year ago |
|
lhez
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
1 year ago |
