freeliuzc 9018ccf74e [Speculative Decoding] Fix attn_mask_offset for multi-step MTP in mixed and PD-split modes (#5738) ...

* fix attn_mask_offset in mtp with multi-step and pd-split-mode

* fix xpu operater register

* update pmtp multi-step mtp strategy in d-split -mode

* add note

* fix xpu register

2025-12-25 01:54:59 -08:00

..

draft_model_postprocess.cu

…

draft_model_preprocess.cu

[Speculative Decoding] Fix attn_mask_offset for multi-step MTP in mixed and PD-split modes (#5738)

2025-12-25 01:54:59 -08:00

draft_model_set_value_by_flags.cu

…

draft_model_update.cu

…

eagle_get_hidden_states.cu

rename eagle_get_base_model_hidden_states.cu (#3753)

2025-09-07 10:24:58 +08:00

eagle_get_self_hidden_states.cu

…

hydra_fetch_hidden_states.cu

…

mtp_save_first_token.cc

support mtp in splitewise and scheduler_v1 mode (#4743)

2025-11-03 10:07:15 +08:00

mtp_step_paddle.cu

…

ngram_match_mixed.cu

…