0.1.22

What's Changed

• updated llama.cpp by @github-actions in #50
• updated llama.cpp by @github-actions in #52

Full Changelog: 0.1.21...0.1.22

0.1.21

What's Changed

• updated llama.cpp by @github-actions in #49

Full Changelog: 0.1.20...0.1.21

0.1.20

changed cpp version to 17 (this fixed some issues when compiling with the cuda docker image, not sure why)

Full Changelog: 0.1.19...0.1.20

0.1.19

What's Changed

• updated llama.cpp by @github-actions in #48

Full Changelog: 0.1.18...0.1.19

0.1.18

Added LlamaBatchAdd to LlamaError

Full Changelog: 0.1.17...0.1.18

0.1.17

What's Changed

• Batch add error handeling by @MarcusDunn in #46

Full Changelog: 0.1.16...0.1.17

0.1.16

What's Changed

• added n_batch by @MarcusDunn in #45

Full Changelog: 0.1.15...0.1.16

0.1.15

What's Changed

• config rope scaling by @MarcusDunn in #44

Full Changelog: 0.1.14...0.1.15

0.1.14

What's Changed

• implemented Send + Sync for LlamaContextParams by @MarcusDunn in #43 (fixed regression in 0.1.12)

Full Changelog: 0.1.13...0.1.14

0.1.13

Breaking Changes

Changed how to create and modify LlamaContextParams

What's Changed

• fixed up LlamaContextParams with new CB by @MarcusDunn in #36
• updated llama.cpp by @github-actions in #35
• Bump shlex from 1.1.0 to 1.3.0 by @dependabot in #38
• updated llama.cpp by @github-actions in #40

Full Changelog: 0.1.12...0.1.13