]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bfb1e01)
opencl: add `backend_synchronize` (#13939)
authorlhez <redacted>
Mon, 2 Jun 2025 23:54:58 +0000 (16:54 -0700)
committerGitHub <redacted>
Mon, 2 Jun 2025 23:54:58 +0000 (16:54 -0700)
commit71e74a3ac929b8af91f16f73f3c2b9b2f796d207
tree70c583585b4f893de0ddd2ad49080d1682630ab4tree
parentbfb1e012a0b7658e8f00ed4333d059943ea9d648commit | diff
opencl: add `backend_synchronize` (#13939)

* This is not needed by the normal use where the result is read
  using `tensor_get`, but it allows perf mode of `test-backend-ops`
  to properly measure performance.
ggml/src/ggml-opencl/ggml-opencl.cpp diff | blob | history
Packaging of ggml-org/llama.cpp