0.1.119
What's Changed
- Prevent CUDA and Vulkan incompatibility in
examples/rerankerby adding the expecteddisable_gpuarg by @babichjacob in #807 - Bumped version to 0.1.119 by @github-actions[bot] in #805
- chore(deps): bump anyhow from 1.0.98 to 1.0.99 by @dependabot[bot] in #814
- chore(deps): bump glob from 0.3.2 to 0.3.3 by @dependabot[bot] in #813
- chore(deps): bump clap from 4.5.43 to 4.5.45 by @dependabot[bot] in #811
- chore(deps): bump cc from 1.2.32 to 1.2.34 by @dependabot[bot] in #812
- Add with_n_seq_max and n_seq_max to LlamaContextParams by @darjus in #816
- Add KV cache type (K/V) configuration to LlamaContextParams by @gn64 in #815
New Contributors
Full Changelog: 0.1.118...0.1.119