Implement batched server parity and observability

src/engine/gguf.rs

@@ -46,6 +46,8 @@ pub(super) struct Tensor {
 pub(super) struct Gguf {
     path: PathBuf,
     map: Mmap,
+    data_offset: u64,
+    max_tensor_bytes: u64,
     pub(super) metadata: HashMap<String, Value>,
     pub(super) tensors: HashMap<String, Tensor>,
 }
@@ -141,6 +143,7 @@ impl Gguf {
         }
 
         let data_start = align(cursor.position() as u64, alignment)?;
+        let mut max_tensor_bytes = 0;
         for (name, tensor) in &mut tensors {
             tensor.offset = data_start
                 .checked_add(tensor.offset)
@@ -152,11 +155,14 @@ impl Gguf {
             if end > map.len() as u64 {
                 return Err(format!("tensor {name} points outside the GGUF file"));
             }
+            max_tensor_bytes = max_tensor_bytes.max(tensor.bytes);
         }
 
         Ok(Self {
             path: path.to_owned(),
             map,
+            data_offset: data_start,
+            max_tensor_bytes,
             metadata,
             tensors,
         })
@@ -174,6 +180,14 @@ impl Gguf {
         self.map.as_ptr()
     }
 
+    pub(super) fn data_offset(&self) -> u64 {
+        self.data_offset
+    }
+
+    pub(super) fn max_tensor_bytes(&self) -> u64 {
+        self.max_tensor_bytes
+    }
+
     pub(super) fn tensor(&self, name: &str) -> Result<&Tensor, String> {
         self.tensors
             .get(name)