Use custom chat templates

[ekcasey]

When the model runtime bundle contains a chat template file, use it by passing it to llama.cpp with the --chat-template flag. See CLI PR for usage example.

Related PRs:

• Allow configuration of chat template model-distribution#129
• Allow models to be packaged with custom chat template files model-cli#152

[Copilot]

Pull Request Overview

This pull request adds support for custom chat templates in the llamacpp backend by enabling the use of chat template files from model bundles.

Key changes:

• Adds chat template file support to the llamacpp backend configuration
• Updates the argument generation logic to include --chat-template-file parameter when available
• Updates model-distribution dependency to a newer version

Reviewed Changes

Copilot reviewed 3 out of 4 changed files in this pull request and generated 1 comment.

File	Description
pkg/inference/backends/llamacpp/llamacpp_config.go	Implements chat template file argument handling in completion mode
pkg/inference/backends/llamacpp/llamacpp_config_test.go	Adds test coverage for chat template functionality and updates test bundle
go.mod	Updates model-distribution dependency version

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}