llama.cpp
llama-quantize: Add MoE chunk queue for faster multi-threaded quant creation
#27770

Open

llama-quantize: Add MoE chunk queue for faster multi-threaded quant creation #27770

bartowski1182 wants to merge 1 commit into ggml-org:master from bartowski1182:moe-chunk-queue

Add MoE chunk queue

1a744c9b

bartowski1182 marked this pull request as ready for review 2 days ago

bartowski1182 requested a review from

ggerganov 2 days ago

ngxson assigned

ngxson 1 day ago

bartowski1182 marked this pull request as draft 18 hours ago

Reviewers

ggerganov

Assignees

ngxson

Labels

None yet

Milestone

No milestone