Skip to content

qwen4exp : port NextN/MTP speculative decoding to master (+50% decode at 70k) - #28104

Closed
JayToltTech wants to merge 6 commits into
ggml-org:masterfrom
JayToltTech:feat/qwen4exp-mtp-upstream
Closed

qwen4exp : port NextN/MTP speculative decoding to master (+50% decode at 70k)#28104
JayToltTech wants to merge 6 commits into
ggml-org:masterfrom
JayToltTech:feat/qwen4exp-mtp-upstream

server : keep speculative checkpoints on device

175b66c
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar