diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2023-11-28 10:32:03 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-28 10:32:03 +0200 |
| commit | 8406b0924bf323f37d536dee8b8165c1f3d9d11d (patch) | |
| tree | 23b753a4e289a89c9e511760b8d2e6583fda9768 /examples | |
| parent | b38a16dfcff88d547f78f52d1bea31b84a05aff7 (diff) | |
ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240)
* ggml : use blas even if src0 is not F32
* llama : use n_threads_batch only when n_tokens >= 32
ggml-ci
* llama : revert n_threads_batch logic
ggml-ci
Diffstat (limited to 'examples')
0 files changed, 0 insertions, 0 deletions