llama.cpp
server : fix speculative decoding with context shift
#10641

Merged

server : fix speculative decoding with context shift #10641

ggerganov merged 3 commits into master from gg/server-fix-spec-ctx-shift

server : fix speculative decoding with context shift

a5a915b5

github-actions added examples

github-actions added server

server : take into account speculative limits

b436edaa

ggerganov force pushed to b436edaa 1 year ago

server : add tests

81611bef

github-actions added python

ggerganov requested a review from

ngxson 1 year ago

ngxson approved these changes on 2024-12-04

ggerganov merged 1da7b765 into master 1 year ago

Reviewers

ngxson

Assignees

No one assigned

Labels

examples python server

Milestone

No milestone