0.1.18-25.06.24

What's Changed

• chore: Update llama.cpp submodule to latest release b3218 by @vansangpfiev in #116
• feat: add noavx linux build by @vansangpfiev in #115
• fix: readme by @vansangpfiev in #117

Full Changelog: v0.1.18-22.06.24...v0.1.18-25.06.24

0.1.12-25.06.24

Full Changelog: v0.1.18-25.06.24...v0.1.12-25.06.24

• Customized release to support stable vulkan

0.1.19

Changes

• Update llama.cpp submodule to latest release b3197 @jan-service-account (#114)
• feat: request larger context for llava-v1.6 @vansangpfiev (#105)
• Update llama.cpp submodule to latest release b3188 @jan-service-account (#112)
• Update llama.cpp submodule to latest release b3184 @jan-service-account (#108)
• Update llama.cpp submodule to latest release b3180 @jan-service-account (#104)
• add clean step @hiento09 (#103)

Contributor

@github-actions[bot], @hiento09, @jan-service-account, @sangjanai and @vansangpfiev

0.1.18-22.06.24

What's Changed

• feat: request larger context for llava-v1.6 by @vansangpfiev in #105
• Update llama.cpp submodule to latest release b3197 by @jan-service-account in #114

Full Changelog: v0.1.17-20.06.24...v0.1.18-22.06.24

0.1.17-20.06.24

What's Changed

• Update llama.cpp submodule to latest release b3188 by @jan-service-account in #112

Full Changelog: v0.1.17-19.06.24...v0.1.17-20.06.24

0.1.17-19.06.24

What's Changed

• add clean step by @hiento09 in #103
• Update llama.cpp submodule to latest release b3180 by @jan-service-account in #104
• Update llama.cpp submodule to latest release b3184 by @jan-service-account in #108

Full Changelog: v0.1.18...v0.1.17-19.06.24

0.1.18

Changes

• Update llama.cpp submodule to latest release b3166 @jan-service-account (#102)
• Linux cuda separate cpu instruction and enable sccache @hiento09 (#101)
• feat: add model_path parameter @vansangpfiev (#89)
• Use note auto-generate @hiento09 (#98)
• Correct script create tag @hiento09 (#97)
• Update llama.cpp submodule to latest release b3153 @jan-service-account (#96)
• Change condition checking pr status @hiento09 (#95)
• Correct condition trigger for quality gate @hiento09 (#92)
• Add nightly Build CI @hiento09 (#90)
• Feature sccache for windows local @hiento09 (#85)
• Update llama.cpp submodule to latest release b3140 @jan-service-account (#84)

Contributor

@github-actions[bot], @hiento09, @jan-service-account and @vansangpfiev

0.1.17-15.06.24

What's Changed

• Update llama.cpp submodule to latest release b3140 by @jan-service-account in #84
• Feature sccache for windows local by @hiento09 in #85
• Add nightly Build CI by @hiento09 in #90
• Correct condition trigger for quality gate by @hiento09 in #92
• Change condition checking pr status by @hiento09 in #95
• Update llama.cpp submodule to latest release b3153 by @jan-service-account in #96
• Correct script create tag by @hiento09 in #97

Full Changelog: v0.1.17...v0.1.17-15.06.24

0.1.17

Changes

• feat: enable flash attention by default @vansangpfiev (#82)
• feat: support use_mmap option in parameter @vansangpfiev (#79)
• fix: remove avx2 check since we have it at cortex-cpp layer @vansangpfiev (#78)
• chore: changes windows CI runners @vansangpfiev (#81)
• feat: enable caching by default @vansangpfiev (#77)
• Update llama.cpp submodule to latest release b3091 @jan-service-account (#76)
• feat: add cache_type parameter @vansangpfiev (#75)
• Update llama.cpp submodule to latest release b3088 @jan-service-account (#74)
• fix: use inference stop words by default, fallback to loading model stop words @vansangpfiev (#72)
• feat: add stop words when loading model @vansangpfiev (#71)
• Update llama.cpp submodule to latest release b3078 @jan-service-account (#70)
• Update llama.cpp submodule to latest release b3070 @jan-service-account (#69)
• Update llama.cpp submodule to latest release b3051 @jan-service-account (#68)
• Update llama.cpp submodule to latest release b3040 @jan-service-account (#67)

Contributor

@jan-service-account and @vansangpfiev

0.1.16

Changes

• Update llama.cpp submodule to latest release b3091 @jan-service-account (#76)
• feat: add cache_type parameter @vansangpfiev (#75)
• Update llama.cpp submodule to latest release b3088 @jan-service-account (#74)
• fix: use inference stop words by default, fallback to loading model stop words @vansangpfiev (#72)
• feat: add stop words when loading model @vansangpfiev (#71)
• Update llama.cpp submodule to latest release b3078 @jan-service-account (#70)
• Update llama.cpp submodule to latest release b3070 @jan-service-account (#69)
• Update llama.cpp submodule to latest release b3051 @jan-service-account (#68)
• Update llama.cpp submodule to latest release b3040 @jan-service-account (#67)

Contributor

@jan-service-account and @vansangpfiev