321f628239
Reuse the buffer for the ggml context which is used for creating the compute graph on the server side. This partially addresses a memory leak created by the CUDA backend due to using buffer addresses as cache keys. ref: #21265 ref: #20315 |
||
|---|---|---|
| .. | ||
| cmake | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||