Releases: ggml-org/llama.vscode
Releases · ggml-org/llama.vscode
v0.0.24
Make it possible to disable the popups on startup for installing/upgrading llama.cpp
v0.0.23
- Environment UI added
- -fa option removed from the llama-server calls
- Env extended with agent and some settings (not only models anymore)
v0.0.22
- Fix endless cycle on refusing to install llama.cpp
- Other UX changes.
v0.0.21
- Changes history added
- Chats could be selected, deleted, exported, imported
- llama-vscode UI (agent) is shown in a separate view now, not as part of Explorer view.
v0.0.20
Fix starting the completion model twice on selecting an env
v0.0.19
- Agent entity added - agents with different system prompts and default tools could be selected
- Fixed showing tables in llama agent
- Local envs with gpt-oss 20B added (also available for import from here)
v0.0.18
- Fixed a bug in case no env selected
- Docu updated
- Setting env_start_last_used added to start automatically the last used env on startup
v0.0.17
-
Increase the space for llama agent,
-
fix a bug for showing llama-agent.
-
Update the documentation for llama-vscode
-
Envs with local gpt-oss for agent removed
v0.0.16
- Llama Agent UI improved
- Chat with AI about llama.vscode added
- Markdown is used in llama agent for better visualization
- Orchestra is renamed to env
v0.0.15
-
Adding a model from huggingface implemented. It is available from llama-vscode menu (for all models) and from Llama Agent, frame "Chat With AI", button "Add" (for chat models)
-
Tool llama_vscode_help added. With this tool it is possible to ask AI for information, which is available in llama-vscode wiki pages.
Adding models directly from huggingface is implemented.
A new tool llama_vscode_help is added. With this tool it is possible to ask AI for information, which is available in llama-vscode wiki pages.