chore(deps): update dependency llama-cpp-python to v0.2.89

[renovate]

This PR contains the following updates:

Package	Change	Age	Adoption	Passing	Confidence
llama-cpp-python (changelog)	==0.2.79 -> ==0.2.89

---

Release Notes

abetlen/llama-cpp-python (llama-cpp-python)

v0.2.89

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@cfac111
• fix: Llama.close didn't free lora adapter by @​jkawamoto in #​1679
• fix: missing dependencies for test by @​jkawamoto in #​1680

v0.2.88

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@fc4ca27
• fix: only print 'cache saved' in verbose mode by @​lsorber in #​1668
• fix: Added back from_file method to LlamaGrammar by @​ExtReMLapin in #​1673
• fix: grammar prints on each call by @​abetlen in 0998ea0
• feat: Enable recursive search of HFFS.ls when using from_pretrained by @​benHeidabetlen in #​1656
• feat: Add more detailed log for prefix-match by @​xu-song in #​1659

v0.2.87

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@be55695
• fix: Include all llama.cpp source files and subdirectories by @​abetlen in 9cad571
• feat(ci): Re-build wheel index automatically when releases are created by @​abetlen in 198f47d

v0.2.86

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@398ede5
• feat: Ported back new grammar changes from C++ to Python implementation by @​ExtReMLapin in (#​1637)
• fix: llama_grammar_accept_token arg order by @​tc-wolf in (#​1649)

v0.2.85

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@398ede5
• fix: Missing LoRA adapter after API change by @​shamitv in #​1630
• fix(docker): Update Dockerfile BLAS options by @​olivierdebauche in #​1632
• fix(docker): Fix GGML_CUDA param by @​olivierdebauche in #​1633
• fix(docker): Update Dockerfile build options from LLAMA_ to GGML_ by @​olivierdebauche in #​1634
• feat: FreeBSD compatibility by @​yurivict in #​1635

v0.2.84

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@4730fac
• fix: fix: Correcting run.sh filepath in Simple Docker implementation by @​mashuk999 in #​1626

v0.2.83

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@081fe43
• feat: Add 'required' literal to ChatCompletionToolChoiceOption by @​mjschock in #​1597
• fix: Change repeat_penalty to 1.0 to match llama.cpp defaults by @​ddh0 in #​1590
• fix(docs): Update README.md typo by @​ericcurtin in #​1589
• fix(server): Use split_mode from model settings by @​grider-withourai in #​1594
• feat(ci): Dockerfile update base images and post-install cleanup by @​Smartappli in #​1530

v0.2.82

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@7fdb6f7

v0.2.81

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@9689673
• fix(ci): Fix CUDA wheels, use LLAMA_CUDA instead of removed LLAMA_CUBLAS by @​abetlen in 4fb6fc1
• fix(ci): Fix MacOS release, use macos-12 image instead of removed macos-11 by @​abetlen in 3a551eb

v0.2.80

Compare Source

• feat: Update llama.cpp to ggerganov/llama.cpp@023b880
• fix(server): Fix bug in FastAPI streaming response where dependency was released before request completes causing SEGFAULT by @​abetlen in 296304b
• fix(server): Update default config value for embeddings to False to fix error in text generation where logits were not allocated by llama.cpp by @​abetlen in bf5e0bb
• fix(ci): Fix the CUDA workflow by @​oobabooga in #​1551
• docs: Update readme examples to use newer Qwen2 model by @​jncraton in #​1544

---

Configuration

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

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ 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.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[renovate]

Renovate Ignore Notification

Because you closed this PR without merging, Renovate will ignore this update (==0.2.89). You will get a PR once a newer version is released. To ignore this dependency forever, add it to the ignoreDeps array of your Renovate config.

If you accidentally closed this PR, or if you changed your mind: rename this PR to get a fresh replacement PR.