llama.cpp
Q4_2 quantization with rmse-optimized scale and quants
#1062

Merged

Q4_2 quantization with rmse-optimized scale and quants #1062

ikawrakow merged 4 commits into master from quantize-q4-2-rmse

Q4_2 quantization with rmse-optimized scale and quants

6eec0608

ikawrakow requested a review from

ggerganov 3 years ago

ggerganov approved these changes on 2023-04-19

ggml : satisfy the sanitizer builds

6d36a51f

sw commented on 2023-04-19

Better follow ggml conventions for function names

49beb2cd

Fixed type as per reviewer comment

96d84438

Green-Sky commented on 2023-04-19

ikawrakow merged f7d05095 into master 3 years ago

ikawrakow deleted the quantize-q4-2-rmse branch 3 years ago

Reviewers

ggerganov

Green-Sky

Assignees

No one assigned

Labels

None yet

Milestone

No milestone