Files
llama.cpp/tools
Aman Gupta 3e12fbdea5 llama: avoid copying logits during prompt decode in MTP (#23198)
* llama: avoid copying logits during prompt decode in MTP

* review: update comment

* llama-graph: call set_output for t_h_pre_norm
2026-05-17 23:30:25 +08:00
..
2026-05-16 20:06:23 +08:00
2026-05-14 13:05:52 +03:00