mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-13 02:30:36 +01:00
Since the prefill length is not fixed, graphs constructed for the prefill stage cannot be reused. For this reason, ACL graph execution is disabled by default during prefill. |
||
|---|---|---|
| .. | ||
| BLIS.md | ||
| CANN.md | ||
| CUDA-FEDORA.md | ||
| OPENCL.md | ||
| SYCL.md | ||