 0cc4m
|
ef52d1d16a
Update Vulkan RoPE implementation (#7818)
|
1 year ago |
|
0cc4m
|
3d7ebf6312
Vulkan Mixture of Experts (MoE) support (#7628)
|
1 year ago |
 Georgi Gerganov
|
fb76ec31a9
ggml : fix YARN + add tests + add asserts (#7617)
|
1 year ago |
|
0cc4m
|
1b1e27cb49
Update vulkan rope implementation to support frequency factors (#7475)
|
1 year ago |
|
0cc4m
|
f030ec1f7a
Vulkan Embedding Fix (#7360)
|
1 year ago |
|
0cc4m
|
c1b295eea5
Update and fix Vulkan soft_max and argsort implementations (#7237)
|
1 year ago |
|
0cc4m
|
befddd0f15
Vulkan Bugfixes and Improvements (#7084)
|
1 year ago |
 Brian
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
1 year ago |
|
0cc4m
|
ba0c7c70ab
Vulkan k-quant mmq and ggml-backend offload functionality (#6155)
|
1 year ago |
|
0cc4m
|
61d1c88e15
Vulkan Improvements (#5835)
|
1 year ago |
 Neuman Vong
|
4b7b38bef5
vulkan: Set limit for task concurrency (#5427)
|
1 year ago |
|
0cc4m
|
e920ed393d
Vulkan Intel Fixes, Optimizations and Debugging Flags (#5301)
|
2 years ago |
|
0cc4m
|
4d0924a890
Vulkan Phi Fix for AMD Proprietary Drivers (#5260)
|
2 years ago |
|
0cc4m
|
f8e9140cb4
Vulkan Fixes (#5223)
|
2 years ago |
|
0cc4m
|
2307523d32
ggml : add Vulkan backend (#2059)
|
2 years ago |
