llama.cpp
ggml : make quantization bit-reproducible across compilers and architectures (-ffp-contract=off on ggml-quants.c)
#25353
Open
Open
ggml : make quantization bit-reproducible across compilers and architectures (-ffp-contract=off on ggml-quants.c) #25353
theadamdanielsson
wants to merge
1 commit into
ggml-org:master
from
theadamdanielsson:deterministic-quantize-default
Reviewers
No reviews
Assignees
No one assigned
Labels
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub