Complete removal of unused settings from loading model options

Author: jmbejar

moxin-backend/src/backend_impls/chat_ui.rs

@@ -316,22 +316,15 @@ fn create_wasi(
     file: &DownloadedFile,
     load_model: &LoadModelOptions,
 ) -> wasmedge_sdk::WasmEdgeResult<WasiModule> {
-    let ctx_size = if load_model.n_ctx > 0 {
-        Some(load_model.n_ctx.to_string())
-    } else {
-        None
-    };
+    let ctx_size = Some(format!("{}", file.context_size));
 
     let n_gpu_layers = match load_model.gpu_layers {
         moxin_protocol::protocol::GPULayers::Specific(n) => Some(n.to_string()),
         moxin_protocol::protocol::GPULayers::Max => None,
     };
 
-    let batch_size = if load_model.n_batch > 0 {
-        Some(load_model.n_batch.to_string())
-    } else {
-        None
-    };
+    // Set n_batch to a fixed value of 128.
+    let batch_size = Some(format!("128"));
 
     let mut prompt_template = load_model.prompt_template.clone();
     if prompt_template.is_none() && !file.prompt_template.is_empty() {

moxin-backend/src/backend_impls/mod.rs

@@ -136,8 +136,6 @@ fn test_chat() {
             prompt_template: None,
             gpu_layers: moxin_protocol::protocol::GPULayers::Max,
             use_mlock: false,
-            n_batch: 512,
-            n_ctx: 512,
             rope_freq_scale: 0.0,
             rope_freq_base: 0.0,
             context_overflow_policy: moxin_protocol::protocol::ContextOverflowPolicy::StopAtLimit,
@@ -211,8 +209,6 @@ fn test_chat_stop() {
             prompt_template: None,
             gpu_layers: moxin_protocol::protocol::GPULayers::Max,
             use_mlock: false,
-            n_batch: 512,
-            n_ctx: 512,
             rope_freq_scale: 0.0,
             rope_freq_base: 0.0,
             context_overflow_policy: moxin_protocol::protocol::ContextOverflowPolicy::StopAtLimit,

moxin-protocol/src/protocol.rs

@@ -28,8 +28,6 @@ pub struct LoadModelOptions {
     pub prompt_template: Option<String>,
     pub gpu_layers: GPULayers,
     pub use_mlock: bool,
-    pub n_batch: u32,
-    pub n_ctx: u32,
     pub rope_freq_scale: f32,
     pub rope_freq_base: f32,
 

src/data/chats/mod.rs

@@ -59,8 +59,6 @@ impl Chats {
                 prompt_template: None,
                 gpu_layers: moxin_protocol::protocol::GPULayers::Max,
                 use_mlock: false,
-                n_batch: 512,
-                n_ctx: 512,
                 rope_freq_scale: 0.0,
                 rope_freq_base: 0.0,
                 context_overflow_policy: