huicongyao 25d64efdc4 [Speculative Decoding] Refactor Eagle MTP hidden states copy (#6812) ...

* reformat eagle_get_hidden_states & eagle_get_self_hidden_states

* readibility

* fix xpu bug

* fix coverage failure

* change luanch params & parallelize position_map compute

* Fix MTP-related bugs in FastDeploy centralized inference

* fix

* refactor mtp hidden_states process

* fix

* add unittest & optimize kernel

* remove useless code

* fix

2026-03-25 22:54:31 -07:00

..

__init__.py

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

base.py

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

mtp.py

[Speculative Decoding] Refactor Eagle MTP hidden states copy (#6812)

2026-03-25 22:54:31 -07:00

ngram.py

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

suffix.py

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

types.py

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00