llama.cpp
quantize: be able to explicitly specify quantization type of output and token embedding tensors
#6239

Merged

quantize: be able to explicitly specify quantization type of output and token embedding tensors #6239

ggerganov merged 2 commits into master from ik/quantize_not_repeating

quantize: be able to specify the output tensor type

7883796f

quantize: be able to specify the token embedding tensor type

0e826d12

slaren approved these changes on 2024-03-22

ggerganov approved these changes on 2024-03-22

ggerganov merged 1d0331c1 into master 1 year ago

Reviewers

ggerganov

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone