Samuel Oliveira Alves 557b674f63 Add llama_context to MTP (#1601) ...

* wip: separate llama_context for MTP with graph reuse

* wip: fix KV cache desync with separate MTP context

* refactor: remove dead mtp logic code, encapsulate KV mirroring

* mtp-context: derive args directly from the main model's context

* mtp: fix kv cache positions

* clean small comments

* minor refactor for context shift

2026-04-09 15:33:56 +02:00

163 KiB

Raw Blame History

View Raw