llama.cpp
ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product
#23961

Merged

ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product #23961

am17an merged 1 commit into ggml-org:master from ragz4125:feat_nvfp4_avx

ragz4125 requested a review from

ggerganov 109 days ago

github-actions added ggml

ragz4125 changed the title ~~ggml: add AVX2 and AVX optimization for nvfp4 dot product~~ ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product 109 days ago

ragz4125 force pushed 108 days ago

ragz4125 force pushed 101 days ago

ragz4125 force pushed 85 days ago

am17an commented on 2026-06-25

ragz4125 force pushed 82 days ago

am17an approved these changes on 2026-06-30

ggml-cpu: add AVX2 optimization for nvfp4 dot product and use UE4M3 LUT

54a19a63

ragz4125 force pushed to 54a19a63 80 days ago

CISC approved these changes on 2026-06-30

am17an merged 6dbc1174 into master 79 days ago

Reviewers

CISC

am17an

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone

llama.cpp ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product #23961 Merged

ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product #23961

llama.cpp
ggml-cpu : add AVX2 and AVX optimization for nvfp4 dot product
#23961

Merged