c29e86fc9d
[Feature] Support mtp overlap schedule ( #7001 )
2026-04-01 14:24:26 +08:00
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
e87ce4b8cd
[Speculative Decoding] refactor MTP and optimize spec-decoding postprocess ( #6973 )
...
* support new mtp
* refactor(speculate_decoding and mtp): optimize mtp sturcture logic. Update spec-branch status-process
* fix cuda-graph for spec-decoding
* fix xpu mtp and fix some note
* fix unittest and optmize note
* fix model status update in eos-branch
2026-03-24 10:19:01 +08:00
2b4748de4f
[MTP] refactor MTP pre_process ( #6358 )
2026-02-09 10:47:15 +08:00
ef4a1aa2da
【Hackathon 9th No.61、65】add test_draft_model_update ( #3940 )
...
* add draft_model_update test
* fix
* fix
* fix
* fix
* fix
2025-09-15 11:19:50 +08:00
sunxin