search

allenporter / llama-cpp-server

Docker images for easier running of llama-cpp-python server
Apache License 2.0
5 stars 2 forks source link

Update dependency llama_cpp_python to v0.2.73 #68

Closed renovate[bot] closed 6 months ago

renovate[bot] commented 6 months ago

Mend Renovate

This PR contains the following updates:

Package Change Age Adoption Passing Confidence
llama_cpp_python (changelog) ==0.2.69 -> ==0.2.73 age adoption passing confidence

Release Notes

abetlen/llama-cpp-python (llama_cpp_python) ### [`v0.2.73`](https://togithub.com/abetlen/llama-cpp-python/blob/HEAD/CHANGELOG.md#0273) [Compare Source](https://togithub.com/abetlen/llama-cpp-python/compare/v0.2.72...v0.2.73) - feat: Update llama.cpp to [ggerganov/llama.cpp@`25c6e82`](https://togithub.com/ggerganov/llama.cpp/commit/25c6e82e7a1ad25a42b0894e87d9b5c557409516) - fix: Clear kv cache at beginning of image chat formats to avoid bug when image is evaluated first by [@​abetlen](https://togithub.com/abetlen) in [`ac55d0a`](https://togithub.com/abetlen/llama-cpp-python/commit/ac55d0a175115d1e719672ce1cb1bec776c738b1) ### [`v0.2.72`](https://togithub.com/abetlen/llama-cpp-python/blob/HEAD/CHANGELOG.md#0272) [Compare Source](https://togithub.com/abetlen/llama-cpp-python/compare/v0.2.71...v0.2.72) - fix(security): Remote Code Execution by Server-Side Template Injection in Model Metadata by [@​retr0reg](https://togithub.com/retr0reg) in [`b454f40`](https://togithub.com/abetlen/llama-cpp-python/commit/b454f40a9a1787b2b5659cd2cb00819d983185df) - fix(security): Update remaining jinja chat templates to use immutable sandbox by [@​CISC](https://togithub.com/CISC) in [#​1441](https://togithub.com/abetlen/llama-cpp-python/issues/1441) ### [`v0.2.71`](https://togithub.com/abetlen/llama-cpp-python/blob/HEAD/CHANGELOG.md#0271) [Compare Source](https://togithub.com/abetlen/llama-cpp-python/compare/v0.2.70...v0.2.71) - feat: Update llama.cpp to [ggerganov/llama.cpp@`911b390`](https://togithub.com/ggerganov/llama.cpp/commit/911b3900dded9a1cfe0f0e41b82c7a29baf3a217) - fix: Make leading bos_token optional for image chat formats, fix nanollava system message by [@​abetlen](https://togithub.com/abetlen) in [`7712263`](https://togithub.com/abetlen/llama-cpp-python/commit/77122638b4153e31d9f277b3d905c2900b536632) - fix: free last image embed in llava chat handler by [@​abetlen](https://togithub.com/abetlen) in [`3757328`](https://togithub.com/abetlen/llama-cpp-python/commit/3757328b703b2cd32dcbd5853271e3a8c8599fe7) ### [`v0.2.70`](https://togithub.com/abetlen/llama-cpp-python/blob/HEAD/CHANGELOG.md#0270) [Compare Source](https://togithub.com/abetlen/llama-cpp-python/compare/v0.2.69...v0.2.70) - feat: Update llama.cpp to [ggerganov/llama.cpp@`c0e6fbf`](https://togithub.com/ggerganov/llama.cpp/commit/c0e6fbf8c380718102bd25fcb8d2e55f8f9480d1) - feat: fill-in-middle support by [@​CISC](https://togithub.com/CISC) in [#​1386](https://togithub.com/abetlen/llama-cpp-python/issues/1386) - fix: adding missing args in create_completion for functionary chat handler by [@​skalade](https://togithub.com/skalade) in [#​1430](https://togithub.com/abetlen/llama-cpp-python/issues/1430) - docs: update README.md [@​eltociear](https://togithub.com/eltociear) in [#​1432](https://togithub.com/abetlen/llama-cpp-python/issues/1432) - fix: chat_format log where auto-detected format prints None by [@​balvisio](https://togithub.com/balvisio) in [#​1434](https://togithub.com/abetlen/llama-cpp-python/issues/1434) - feat(server): Add support for setting root_path by [@​abetlen](https://togithub.com/abetlen) in [`0318702`](https://togithub.com/abetlen/llama-cpp-python/commit/0318702cdc860999ee70f277425edbbfe0e60419) - feat(ci): Add docker checks and check deps more frequently by [@​Smartappli](https://togithub.com/Smartappli) in [#​1426](https://togithub.com/abetlen/llama-cpp-python/issues/1426) - fix: detokenization case where first token does not start with a leading space by [@​noamgat](https://togithub.com/noamgat) in [#​1375](https://togithub.com/abetlen/llama-cpp-python/issues/1375) - feat: Implement streaming for Functionary v2 + Bug fixes by [@​jeffrey-fong](https://togithub.com/jeffrey-fong) in [#​1419](https://togithub.com/abetlen/llama-cpp-python/issues/1419) - fix: Use memmove to copy str_value kv_override by [@​abetlen](https://togithub.com/abetlen) in [`9f7a855`](https://togithub.com/abetlen/llama-cpp-python/commit/9f7a85571ae80d3b6ddbd3e1bae407b9f1e3448a) - feat(server): Remove temperature bounds checks for server by [@​abetlen](https://togithub.com/abetlen) in [`0a454be`](https://togithub.com/abetlen/llama-cpp-python/commit/0a454bebe67d12a446981eb16028c168ca5faa81) - fix(server): Propagate flash_attn to model load by [@​dthuerck](https://togithub.com/dthuerck) in [#​1424](https://togithub.com/abetlen/llama-cpp-python/issues/1424)

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Enabled.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

This PR has been generated by Mend Renovate. View repository job log here.