llama.cpp
model: Minimax M3, Replace the CPU OP during prefill
#26297

Merged

model: Minimax M3, Replace the CPU OP during prefill #26297

am17an merged 1 commit into ggml-org:master from timkhronos:MSA-Backend-Prefill

Remove custom cpu op from the M3 graph, express with stock ops

d6ef681d

timkhronos requested a review from

CISC 53 days ago

github-actions added model

ngxson approved these changes on 2026-07-29

am17an approved these changes on 2026-07-30

am17an merged b2f22168 into master 53 days ago

timkhronos deleted the MSA-Backend-Prefill branch 52 days ago

Reviewers

am17an

ngxson

CISC

Assignees

No one assigned

Labels

model

Milestone

No milestone