llama.cpp
IQ2 creation speedup through caching
#31910
Merged

IQ2 creation speedup through caching #31910

bartowski1182
bartowski1182 IQ2 quant creation speedup from caching
62388de1
bartowski1182 Rename variables for clarity
5e898523
bartowski1182 Merge branch 'ggml-org:master' into iq2-cache
b10278ca
bartowski1182 bartowski1182 requested a review from ggerganov ggerganov 11 days ago
github-actions github-actions added ggml
bartowski1182 Explicit casts
4ccdddf1
bartowski1182
ggml-gh-bot
bartowski1182 Initialize all values, add comment to tolerance
1514a264
bartowski1182
CISC
CISC approved these changes on 2026-11-17
bartowski1182
ggerganov ggerganov merged 76f186df into master 1 day ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone