llama.cpp
Vulkan Optimizations and Fixes
#8959
Merged

Vulkan Optimizations and Fixes #8959

0cc4m merged 9 commits into master from 0cc4m/vulkan-optimization
0cc4m
0cc4m Optimize Vulkan REPEAT performance
0645ed5c
0cc4m Use Vulkan GLSL fused multiply-add instruction where possible
f78487b8
0cc4m Add GGML_VULKAN_PERF option to output performance data per operator
4c6a7bb0
0cc4m Rework and fix Vulkan descriptor set and descriptor pool handling
efe6aca5
0cc4m Fix float32 concat f16 shader validation error
9e0ac989
github-actions github-actions added Vulkan
github-actions github-actions added ggml
mofosyne mofosyne added Review Complexity : Medium
mofosyne mofosyne added performance
mofosyne mofosyne added bugfix
0cc4m Add Vulkan GROUP_NORM eps parameter
61d83887
0cc4m Merge upstream changes, fix conflicts
4f197e33
0cc4m Fix validation error with transfer queue memory barrier flags
5ae33eb9
0cc4m 0cc4m marked this pull request as ready for review 1 year ago
0cc4m
ggerganov
ggerganov commented on 2024-08-11
0cc4m 0cc4m requested a review from ggerganov ggerganov 1 year ago
0cc4m
slaren
slaren approved these changes on 2024-08-14
ggerganov
ggerganov approved these changes on 2024-08-14
0cc4m Remove trailing whitespaces
12d214f4
0cc4m 0cc4m merged 5fd89a70 into master 1 year ago
0cc4m 0cc4m deleted the 0cc4m/vulkan-optimization branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone