Update dependency de.kherud:llama to v3.2.1

[renovate]

This PR contains the following updates:

Package	Change	Age	Adoption	Passing	Confidence
de.kherud:llama	3.0.2 -> 3.2.1

---

Release Notes

kherud/java-llama.cpp (de.kherud:llama)

v3.2.1: Version 3.2.1

Compare Source

• Include GGML backend in text log
• Update to llama.cpp b3008

v3.2.0: Version 3.2.0

Compare Source

Logging Re-Implementation (see #​66)

• Re-adds logging callbacks via LlamaModel#setLogger(LogFormat, BiConsumer<LogLevel, String>)
• Removes dis-functional ModelParameters#setLogDirectory(String), ModelParameters#setDisableLog(boolean), andModelParameters#setLogFormat(LogFormat)

v3.1.1: Version 3.1.1

Compare Source

• Adds chat template support (credit to @​lesters #​64)
• Updates to llama.cpp b2969
• Adds explicit Phi-3 128k support

v3.1.0: Version 3.1.0

Compare Source

Changes:

• Updates to llama.cpp b2885
• Fixes #​62 (generation can now be canceled)
• Fixes macos x64 shared libraries

API changes:

• LlamaModel.Output is now LlamaOutput
• LlamaIterator is now public, was private LlamaModel.Iterator previously

---

Configuration

📅 Schedule: Branch creation - "before 6am on thursday" (UTC), 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 has been generated by Mend Renovate. View repository job log here.

[baldersheim]

Depends on vespa-engine/vespa-3rdparty-deps#247 and subsequent successful copr build.