llama.cpp
server : add speculative decoding support
#10455
Merged

server : add speculative decoding support #10455

ggerganov merged 2 commits into master from gg/speculative-server
ggerganov
github-actions github-actions added examples
github-actions github-actions added server
ggerganov ggerganov force pushed 1 year ago
3Simplex
ggerganov ggerganov force pushed 1 year ago
ggerganov ggerganov force pushed 1 year ago
ggerganov ggerganov force pushed 1 year ago
ggerganov ggerganov force pushed 1 year ago
ggerganov ggerganov force pushed 1 year ago
ggerganov ggerganov marked this pull request as ready for review 1 year ago
ggerganov
3Simplex
mostlygeek
ggerganov ggerganov force pushed 1 year ago
ggerganov
mostlygeek
mostlygeek
ggerganov
mostlygeek
ggerganov
3Simplex
mostlygeek
ggerganov
Base automatically changed from gg/speculative-refactor to master 1 year ago
ggerganov server : add speculative decoding support
156aa6d9
ggerganov ggerganov force pushed to 156aa6d9 1 year ago
ggerganov server : add helper function slot.can_speculate()
0ba40c36
sorasoras
ggerganov ggerganov merged 9ca2e677 into master 1 year ago
ggerganov ggerganov deleted the gg/speculative-server branch 1 year ago
mostlygeek
ggerganov
Mushoz
Mushoz
pnb
Mushoz
johnbean393
pnb
mostlygeek
Mushoz
dagbdagb
vitobotta
ggerganov
HabermannR
JeroenAdam
slaren
ggerganov
vitobotta
Mushoz
vitobotta
ggerganov
vitobotta
JeroenAdam
vitobotta
HabermannR
JohannesGaessler
Gobz
ggerganov
ggerganov
Gobz
dagbdagb
slaren
cb88
HabermannR
countzero
Gomez12
JohannesGaessler
ggerganov
Gomez12
vitobotta
PkmX
ggerganov
Mushoz
Mushoz
ggerganov
countzero
ggerganov
countzero
JeroenAdam
webbigdata-jp
dagbdagb
webbigdata-jp
mybyte
JeroenAdam
ggerganov
ggerganov
mybyte
David-AU-github
Mushoz
David-AU-github
Mushoz
David-AU-github
Mushoz
David-AU-github
Mushoz
Mushoz
David-AU-github
firelex
firelex
ggerganov
firelex
firelex
firelex
firelex
firelex
firelex
saood06

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone