Align DeepSeek and GLM execution with DS4

src/engine/gguf.rs

@@ -3,6 +3,7 @@ use sha2::{Digest, Sha256};
 use std::collections::HashMap;
 use std::fs::File;
 use std::path::{Path, PathBuf};
+use std::sync::Arc;
 
 const MAGIC: u32 = 0x4655_4747;
 const MAX_COUNT: u64 = 1_000_000;
@@ -48,7 +49,7 @@ pub(super) struct Tensor {
 
 pub(super) struct Gguf {
     path: PathBuf,
-    map: Mmap,
+    map: Arc<Mmap>,
     data_offset: u64,
     max_tensor_bytes: u64,
     pub(super) metadata: HashMap<String, Value>,
@@ -169,7 +170,7 @@ impl Gguf {
 
         Ok(Self {
             path: path.to_owned(),
-            map,
+            map: Arc::new(map),
             data_offset: data_start,
             max_tensor_bytes,
             metadata,
@@ -215,6 +216,10 @@ impl Gguf {
         self.map.as_ptr()
     }
 
+    pub(super) fn shared_map(&self) -> Arc<Mmap> {
+        Arc::clone(&self.map)
+    }
+
     pub(super) fn data_offset(&self) -> u64 {
         self.data_offset
     }