Aman Gupta 4e732e0a6c llama: allow partial seq_rm for GDN models for speculative decoding ...

Currently speculative checkpoint needs to restart from a checkpoint
after some draft tokens are not accepted, this leads to some wastage in
running the target again. This PR adds the ability to rollback upto
`draft_max` by storing the GDN intermediates.

2026-05-14 11:32:23 +08:00

..

llama-cpp.h

llama : re-enable manual LoRA adapter free (#19983)

2026-03-18 12:03:26 +02:00

llama.h

llama: allow partial seq_rm for GDN models for speculative decoding

2026-05-14 11:32:23 +08:00