diff options
| author | slaren <slarengh@gmail.com> | 2024-03-18 11:03:04 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-18 11:03:04 +0100 |
| commit | 2bf8d0f7c4cc1235755ad06961ca761e458c5e55 (patch) | |
| tree | d2a462deb3c0e34cfb26eab6881a65bfb9fc3b28 /ggml-kompute.cpp | |
| parent | 496bc79bc2b79bfd6124b8687a8dbd6a646e9b06 (diff) | |
backend : offload large batches to GPU (#6083)
* backend : offload large batches to GPU
* fix hip
* code cleanup
* fix CUDA split buffers
* Update ggml-backend-impl.h
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* cuda : fix memset without set_device
* imatrix : remove sched affix from weight names
* sched : add a new split if the current one has too many inputs
reduce max inputs per split
more cleanup
* update backends
ggml-ci
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Diffstat (limited to 'ggml-kompute.cpp')
| -rw-r--r-- | ggml-kompute.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-kompute.cpp b/ggml-kompute.cpp index 4caf2c9e..81dd5067 100644 --- a/ggml-kompute.cpp +++ b/ggml-kompute.cpp @@ -1951,6 +1951,7 @@ static struct ggml_backend_i kompute_backend_i = { /* .graph_plan_compute = */ NULL, /* .graph_compute = */ ggml_backend_kompute_graph_compute, /* .supports_op = */ ggml_backend_kompute_supports_op, + /* .offload_op = */ NULL, /* .event_new = */ NULL, /* .event_free = */ NULL, /* .event_record = */ NULL, |