Files
llama.cpp/common/arg.cpp
Gaurav Garg ad27757261 Move to backend sampling for MTP draft path (#23287)
* Move to backend sampling for MTP draft path

Run top_k(10) on the draft backend. D2H transfers happen only for the top 10 logits

Make backend sampling more robust and fallback to CPU on failure cases, such as with "-sm tensor" or when a backend doesn't support TOP_K.

* Allow sampler chains to be partially offloaded to backend

* Add --spec-draft-backend-sampling argument. Enabled by default.
2026-05-20 22:34:45 +05:30

187 KiB