ggml : Q4_2 ARM #1046

ggerganov merged 5 commits into master from q4_2-arm
ggerganov
ggerganov ggerganov force pushed from 0b575b62 to bbd29211 2 years ago
ggerganov ggerganov marked this pull request as ready for review 2 years ago
ggerganov ggerganov added generation quality
ggerganov ggerganov requested a review from sw sw 2 years ago
ggerganov
ggerganov commented on 2023-04-18
prusnak
prusnak requested changes on 2023-04-18
prusnak
ggerganov
sw
prusnak
ggerganov ggml : Q4_2 ARM
e435b814
ggerganov ggml : add ggml_is_quantized()
fe859297
ggerganov llama : update llama_type_name() with Q4_2 entry
5e6b62ce
ggerganov ggml : speed-up q4_2
3a790894
ggerganov ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32
5843b45b
ggerganov ggerganov force pushed from f30dbf9a to 5843b45b 2 years ago
ggerganov
ggerganov ggerganov merged 77a73403 into master 2 years ago
ggerganov ggerganov deleted the q4_2-arm branch 2 years ago
prusnak
ggerganov ggerganov assigned ggerganov ggerganov 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
Labels
Milestone