Open
Conversation
This commit add a new command to show the status of the Llama plugin. It will show the status of the FIM server and the instruction server (if configured). For example, if both servers are running: ```console :LlamaStatus FIM model: ✅ Ready, Instruction model: ✅ Ready ``` If the server is not running: ```console LlamaStatus: ❌ Server not reachable ``` If one server is not running: ```console FIM model: ✅ Ready, Instruction model: ❌ Not loaded ```
lavilao
added a commit
to lavilao/llama.vim
that referenced
this pull request
Feb 9, 2026
Add fim_template configuration option to support models like Falcon-H1-Tiny
that use a custom FIM format and don't support the /infill endpoint.
- Add fim_template config option with placeholder substitution
- Use completion endpoint format when custom template is configured
- Support both Handlebars-style ({{{prefix}}}) and simple ({prefix}) placeholders
- Update documentation with Falcon-H1-Tiny example configuration
Example usage for Falcon-H1-Tiny:
fim_template = '<|prefix|>{{{prefix}}}<|suffix|>{{{suffix}}}<|middle|>'
endpoint_fim = 'http://localhost:8080/completion'
This commit adds the name of the fim/instruct model to the status output as it can be useful if the server has many models loaded. Example output: ```console FIM model (fim_model): ✅ Ready, Instruction model (qwen_coder_model): ✅ Ready ```
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This commit add a new command to show the status of the Llama plugin. It will show the status of the FIM server and the instruction server (if configured).
For example, if both servers are running:
If the server is not running:
LlamaStatus: ❌ Server not reachableIf one server is not running:
FIM model (fim_model) ✅ Ready, Instruction model: ❌ Not loaded