Skip to content

armgit / zed

Public Imported from GitHub
0

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

language_models: Rename llama.cpp provider ID (#60112)

Ben Brandt3bb922014ecc
diff --git a/assets/settings/default.json b/assets/settings/default.json
index 059608ae046..e6842ae4fa9 100644
--- a/assets/settings/default.json
+++ b/assets/settings/default.json
@@ -2427,7 +2427,7 @@
"ollama": {
"api_url": "http://localhost:11434",
},
- "llama_cpp": {
+ "llama.cpp": {
"api_url": "http://localhost:8080",
},
"openai": {
diff --git a/crates/language_models/src/provider/llama_cpp.rs b/crates/language_models/src/provider/llama_cpp.rs
index 935ec74f9a4..921a2ae63e5 100644
--- a/crates/language_models/src/provider/llama_cpp.rs
+++ b/crates/language_models/src/provider/llama_cpp.rs
@@ -36,7 +36,7 @@ use crate::AllLanguageModelSettings;
const LLAMA_CPP_DOWNLOAD_URL: &str = "https://llama.app";
const LLAMA_CPP_MODELS_URL: &str = "https://huggingface.co/models?library=gguf&sort=trending";
-const PROVIDER_ID: LanguageModelProviderId = LanguageModelProviderId::new("llama_cpp");
+const PROVIDER_ID: LanguageModelProviderId = LanguageModelProviderId::new("llama.cpp");
const PROVIDER_NAME: LanguageModelProviderName = LanguageModelProviderName::new("llama.cpp");
const API_KEY_ENV_VAR_NAME: &str = "LLAMACPP_API_KEY";
@@ -448,7 +448,7 @@ fn display_name_for(id: &str) -> String {
}
fn telemetry_id_for(id: &str) -> String {
- format!("llama_cpp/{}", display_name_for(id))
+ format!("{PROVIDER_ID}/{}", display_name_for(id))
}
impl LlamaCppLanguageModelProvider {
@@ -1656,13 +1656,13 @@ mod tests {
fn telemetry_id_strips_local_model_paths() {
assert_eq!(
telemetry_id_for("/Users/alice/models/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf"),
- "llama_cpp/Qwen2.5-Coder-7B-Instruct-Q4_K_M"
+ "llama.cpp/Qwen2.5-Coder-7B-Instruct-Q4_K_M"
);
assert_eq!(
telemetry_id_for(r"C:\Users\alice\models\Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf"),
- "llama_cpp/Qwen2.5-Coder-7B-Instruct-Q4_K_M"
+ "llama.cpp/Qwen2.5-Coder-7B-Instruct-Q4_K_M"
);
- assert_eq!(telemetry_id_for("my-alias"), "llama_cpp/my-alias");
+ assert_eq!(telemetry_id_for("my-alias"), "llama.cpp/my-alias");
}
#[test]
diff --git a/crates/settings_content/src/language_model.rs b/crates/settings_content/src/language_model.rs
index ab11097728c..e58f3dcc02b 100644
--- a/crates/settings_content/src/language_model.rs
+++ b/crates/settings_content/src/language_model.rs
@@ -15,6 +15,7 @@ pub struct AllLanguageModelSettingsContent {
pub bedrock: Option<AmazonBedrockSettingsContent>,
pub deepseek: Option<DeepseekSettingsContent>,
pub google: Option<GoogleSettingsContent>,
+ #[serde(rename = "llama.cpp")]
pub llama_cpp: Option<LlamaCppSettingsContent>,
pub lmstudio: Option<LmStudioSettingsContent>,
pub mistral: Option<MistralSettingsContent>,
diff --git a/docs/src/ai/use-a-local-model.md b/docs/src/ai/use-a-local-model.md
index 89984d10f34..5ffc60172cc 100644
--- a/docs/src/ai/use-a-local-model.md
+++ b/docs/src/ai/use-a-local-model.md
@@ -39,7 +39,7 @@ Zed automatically discovers the served models with their context length and tool
```json [settings]
{
"language_models": {
- "llama_cpp": {
+ "llama.cpp": {
"api_url": "http://localhost:8080",
"auto_discover": false,
"available_models": [
@@ -63,7 +63,7 @@ Zed uses the context length the server reports (`/props`). Override it for all m
```json [settings]
{
"language_models": {
- "llama_cpp": {
+ "llama.cpp": {
"context_window": 8192
}
}