llama.cpp
ggml : fix quantized cpy op
#12310
Merged

ggml : fix quantized cpy op #12310

ggerganov merged 5 commits into master from gg/cpu-fix-cpy-q
ggerganov
github-actions github-actions added testing
github-actions github-actions added ggml
aviallon
slaren
slaren commented on 2025-03-10
jukofyork
ggerganov
slaren
slaren commented on 2025-03-11
ggerganov
ggerganov commented on 2025-03-11
ggerganov
ggerganov commented on 2025-03-11
slaren
ggerganov ggerganov force pushed 1 year ago
ggerganov
ggerganov ggml : fix quantized cpy op
fb73be13
ggerganov tests : add cpy tests for all types
b5f5b07a
ggerganov tests : add BF16 copy tests
ad62ba1c
ggerganov tests : fix loop for same-type copy
b3be71a1
ggerganov tests : add option to permute the dst tensor
d266584a
ggerganov ggerganov force pushed to d266584a 1 year ago
slaren
slaren approved these changes on 2025-03-21
ggerganov ggerganov merged ba932dfb into master 1 year ago
ggerganov ggerganov deleted the gg/cpu-fix-cpy-q branch 1 year ago
aviallon

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone