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

..

__init__.py

[xpu] support mtp for xpu(mix) (#5274)

2025-12-01 11:03:14 +08:00

base.py

[Speculative Decoding][MTP]Support attn mask offset (#4641)

2025-11-03 10:08:01 +08:00

mtp.py

[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

ngram.py

[Executor]CUDAGraph support Speculate Decode (#3769)

2025-10-09 21:18:29 +08:00