llama.cpp
llama/ggml: multi-GPU pipeline parallelism (xdev host staging) + faster model loading
#19922

Closed

llama/ggml: multi-GPU pipeline parallelism (xdev host staging) + faster model loading #19922

mxxm-t wants to merge 1 commit into ggml-org:master from mxxm-t:pipeline-parallelism

pipeline-parallelism: xdev host staging + load-time toggles

dee003ea

mxxm-t requested a review from

CISC 9 days ago

mxxm-t requested a review from

ggerganov 9 days ago

github-actions added Nvidia GPU

github-actions added ggml

mxxm-t closed this 4 days ago

Reviewers

CISC

ggerganov

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone