llama.cpp
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl
#11166
Merged

vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl #11166

0cc4m merged 3 commits into ggml-org:master from jeffbolznv:copy-to-quant
jeffbolznv
jeffbolznv vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl
924bccc2
jeffbolznv jeffbolznv requested a review from 0cc4m 0cc4m 1 year ago
github-actions github-actions added Vulkan
github-actions github-actions added ggml
jeffbolznv
stduhpf
jeffbolznv
slaren
jeffbolznv
slaren
jeffbolznv
jeffbolznv vulkan: support copy from q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl to f32
305dc666
github-actions github-actions added testing
jeffbolznv
slaren
slaren commented on 2025-01-11
jeffbolznv ggml: copy q->f32 assumes some contiguity in the destination
0a982a41
slaren
slaren approved these changes on 2025-01-13
0cc4m
0cc4m approved these changes on 2025-01-16
0cc4m 0cc4m merged bd38ddea into master 1 year ago
stduhpf
0cc4m
jeffbolznv
stduhpf
jeffbolznv
stduhpf
jeffbolznv
stduhpf
jeffbolznv
stduhpf
jeffbolznv

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone