mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-11-01 03:11:22 +00:00
* hex-bufs: add support for alloc_buffer_n * hex-bufs: add support for splitting large tensors into separate buffers * hex-bufs: update GGML_HEXAGON_MBUF to accept three values dyn,static,total * hex-bufs: bump dyn. default to 512MB since 128MB causes perf regressions with big MOEs * hex-run: add --no-embd-offload option to simplify command lines on devices that need it * Update scripts/snapdragon/run.py Co-authored-by: Jhen-Jie Hong <iainst0409@gmail.com> --------- Co-authored-by: Jhen-Jie Hong <iainst0409@gmail.com> |
||
|---|---|---|
| .. | ||
| adb | ||
| qdc | ||
| build.py | ||
| ggml-hexagon-align-macros.py | ||
| ggml-hexagon-inspect.py | ||
| ggml-hexagon-profile.py | ||
| ggml-hexagon-trace.py | ||
| run.py | ||
| sdk.py | ||
| setup-sdk.py | ||