Bump llama-cpp-2 from 0.1.146 to 0.1.150

[dependabot]

Bumps llama-cpp-2 from 0.1.146 to 0.1.150.

Release notes

Sourced from llama-cpp-2's releases.

0.1.150

What's Changed

• Add opencl feature for the Adreno/Qualcomm GPU backend by @​maumenegaz in utilityai/llama-cpp-rs#1046
• Bumped version to 0.1.150 by @​github-actions[bot] in utilityai/llama-cpp-rs#1045

New Contributors

• @​maumenegaz made their first contribution in utilityai/llama-cpp-rs#1046

Full Changelog: utilityai/llama-cpp-rs@0.1.149...0.1.150

0.1.149

What's Changed

• Bumped version to 0.1.148 by @​github-actions[bot] in utilityai/llama-cpp-rs#1043
• Bumped version to 0.1.149 by @​MarcusDunn in utilityai/llama-cpp-rs#1044

Full Changelog: utilityai/llama-cpp-rs@0.1.148...0.1.149

0.1.148

What's Changed

• chore(deps): bump clap from 4.6.0 to 4.6.1 by @​dependabot[bot] in utilityai/llama-cpp-rs#1010
• expose image_min_tokens and image_max_tokens in MtmdContextParams by @​Roy3838 in utilityai/llama-cpp-rs#1012
• chore(deps): bump llguidance from 1.7.2 to 1.7.5 by @​dependabot[bot] in utilityai/llama-cpp-rs#1019
• chore(deps): bump openssl from 0.10.78 to 0.10.80 by @​dependabot[bot] in utilityai/llama-cpp-rs#1029
• chore(deps): bump toktrie from 1.7.5 to 1.7.6 by @​dependabot[bot] in utilityai/llama-cpp-rs#1036
• chore(deps): bump cc from 1.2.61 to 1.2.64 by @​dependabot[bot] in utilityai/llama-cpp-rs#1030
• feat(build): allow configuring cmake parallelism via ENV by @​t3hmrman in utilityai/llama-cpp-rs#1040
• chore(deps): bump docker/setup-buildx-action from 4.0.0 to 4.1.0 by @​dependabot[bot] in utilityai/llama-cpp-rs#1028
• chore(deps): bump docker/setup-qemu-action from 4.0.0 to 4.1.0 by @​dependabot[bot] in utilityai/llama-cpp-rs#1031
• Add static-openmp and static-stdcxx feature flags by @​bogdanr in utilityai/llama-cpp-rs#1038
• make llguidance sample a eos after the grammar completes by @​AsbjornOlling in utilityai/llama-cpp-rs#1039
• chore(deps): bump llguidance from 1.7.5 to 1.7.6 by @​dependabot[bot] in utilityai/llama-cpp-rs#1041
• chore(deps): bump actions/checkout from 6.0.2 to 6.0.3 by @​dependabot[bot] in utilityai/llama-cpp-rs#1035

New Contributors

• @​Roy3838 made their first contribution in utilityai/llama-cpp-rs#1012
• @​t3hmrman made their first contribution in utilityai/llama-cpp-rs#1040

Full Changelog: utilityai/llama-cpp-rs@0.1.147...0.1.148

0.1.147

What's Changed

• Bumped version to 0.1.147 by @​github-actions[bot] in utilityai/llama-cpp-rs#1016
• chore(deps): bump toktrie from 1.7.2 to 1.7.5 by @​dependabot[bot] in utilityai/llama-cpp-rs#1018
• Add common feature flag to allow slimmer builds by @​bogdanr in utilityai/llama-cpp-rs#1015
• Sync with latest llama.cpp: Remove OpenAI API support, add missing parameter to mtmd stuff, update build.rs by @​AsbjornOlling in utilityai/llama-cpp-rs#1037

New Contributors

• @​bogdanr made their first contribution in utilityai/llama-cpp-rs#1015

... (truncated)

Commits

• 5459e4d Merge pull request #1045 from utilityai/version-bump-0.1.150
• 6d38374 Merge pull request #1046 from maumenegaz/opencl-upstream
• f499bdd feat: add opencl feature (GGML_OPENCL) for the Adreno GPU backend
• 14266a4 Bump version to 0.1.150 [skip ci]
• be4fe9f Merge pull request #1044 from utilityai/version-bump-0.1.149
• 2d62dd5 Bump version to 0.1.149 [skip ci]
• a7e542c Merge pull request #1043 from utilityai/version-bump-0.1.148
• 8059106 Bump version to 0.1.148 [skip ci]
• 447f325 Merge pull request #1035 from utilityai/dependabot/github_actions/actions/che...
• 51bbb62 Merge pull request #1041 from utilityai/dependabot/cargo/llguidance-1.7.6
• Additional commits viewable in compare view