added docs

Author: MarcusDunn

llama-cpp-2/src/context/session.rs

@@ -44,6 +44,10 @@ impl LlamaContext<'_> {
     ///
     /// * `path_session` - The file to save to.
     /// * `tokens` - The tokens to associate the session with. This should be a prefix of a sequence of tokens that the context has processed, so that the relevant KV caches are already filled.
+    /// 
+    /// # Errors
+    /// 
+    /// Fails if the path is not a valid utf8, is not a valid c string, or llama.cpp fails to save the session file.
     pub fn save_session_file(
         &self,
         path_session: impl AsRef<Path>,
@@ -77,6 +81,10 @@ impl LlamaContext<'_> {
     ///
     /// * `path_session` - The file to load from. It must be a session file from a compatible context, otherwise the function will error.
     /// * `max_tokens` - The maximum token length of the loaded session. If the session was saved with a longer length, the function will error.
+    /// 
+    /// # Errors
+    /// 
+    /// Fails if the path is not a valid utf8, is not a valid c string, or llama.cpp fails to load the session file. (e.g. the file does not exist, is not a session file, etc.)
     pub fn load_session_file(
         &mut self,
         path_session: impl AsRef<Path>,
@@ -95,7 +103,7 @@ impl LlamaContext<'_> {
             if llama_cpp_sys_2::llama_load_session_file(
                 self.context.as_ptr(),
                 cstr.as_ptr(),
-                tokens.as_mut_ptr() as *mut i32,
+                tokens.as_mut_ptr().cast::<i32>(),
                 max_tokens,
                 &mut n_out,
             ) {

llama-cpp-2/src/llama_backend.rs

@@ -64,7 +64,7 @@ impl LlamaBackend {
     pub fn init_numa(strategy: NumaStrategy) -> crate::Result<LlamaBackend> {
         Self::mark_init()?;
         unsafe {
-            llama_cpp_sys_2::llama_numa_init(llama_cpp_sys_2::ggml_numa_strategy::from(strategy))
+            llama_cpp_sys_2::llama_numa_init(llama_cpp_sys_2::ggml_numa_strategy::from(strategy));
         }
         Ok(LlamaBackend {})
     }

llama-cpp-2/src/model.rs

@@ -305,6 +305,8 @@ impl LlamaModel {
     /// # Errors
     ///
     /// There is many ways this can fail. See [`LlamaContextLoadError`] for more information.
+    // we intentionally do not derive Copy on `LlamaContextParams` to allow llama.cpp to change the type to be non-trivially copyable.
+    #[allow(clippy::needless_pass_by_value)]
     pub fn new_context(
         &self,
         _: &LlamaBackend,

simple/src/main.rs

@@ -58,7 +58,7 @@ enum Model {
 
 impl Model {
     /// Convert the model to a path - may download from huggingface
-    fn as_path(self) -> Result<PathBuf> {
+    fn get_or_load(self) -> Result<PathBuf> {
         match self {
             Model::Local { path } => Ok(path),
             Model::HuggingFace { model, repo } => ApiBuilder::new()
@@ -97,7 +97,7 @@ fn main() -> Result<()> {
     };
 
     let model_path = model
-        .as_path()
+        .get_or_load()
         .with_context(|| "failed to get model from args")?;
 
     let model = LlamaModel::load_from_file(&backend, model_path, &model_params)