llama.cpp
llama : add a GPU cache for MoE experts kept in host memory
#29887
Merged
Overview
Commits
2
Changes
View On GitHub

llama : add a GPU cache for MoE experts kept in host memory #29887

ggerganov merged 2 commits into ggml-org:master from am17an:aman/moe-cache
am17an
am17an am17an requested a review from ggerganov ggerganov 31 days ago
am17an am17an requested a review 31 days ago
github-actions github-actions added ggml
Green-Sky
Volunteer-1
am17an
sourenaraya
LeoBorcherding
transwarp829
bjude
pashko-k
voidpush
miltos22
am17an
miltos22
am17an am17an requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 30 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-10-04
sasa7812
sasa7812
am17an
voidpush
miltos22
voidpush
miltos22
Atomic-Germ
miltos22
voidpush
miltos22
Atomic-Germ
antomicblitz
am17an llama : add a GPU cache for MoE experts kept in host memory
74db68e0
am17an am17an force pushed to 74db68e0 28 days ago
am17an am17an requested a review from CISC CISC 28 days ago
eisental
am17an
ggerganov ggerganov assigned ggerganov ggerganov 28 days ago
github-actions github-actions added testing
Volunteer-1
miltos22
pwilkin
paulp83
sasa7812
UltraRabbit
am17an
LeoBorcherding
voidpush
sanmai
bjude
paulp83
ggerganov
ggerganov approved these changes on 2026-10-07
lich-77
am17an use llama_moe_cache_ptr
2de17c21
ggerganov ggerganov merged d6cf9acb into master 27 days ago
ggerganov ggerganov added highlight
pwilkin
Volunteer-1
Volunteer-1
dagbdagb
pwilkin
ggerganov
insunaa
sanmai
insunaa
sanmai
insunaa
Atomic-Germ
am17an am17an deleted the aman/moe-cache branch 21 days ago
d-shehu
Volunteer-1
am17an
Atomic-Germ
am17an
d-shehu
Volunteer-1
sanmai
Volunteer-1
Hypfer
am17an
sasa7812

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
Labels
testing ggml highlight
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum