server: improve speed of speculative decoding (#1119)

* server: improve speed of speculative decoding

change logs

rpc: add recompute

spec dec fix

* Fix n_batch_size not set to context size for draft model

---------

Co-authored-by: firecoperana <firecoperana>

examples/server/server-common.h

@@ -336,6 +336,10 @@ public:
 
     llama_pos pos_next() const;
 
+    int n_tokens() const {
+        return tokens.size();
+    }
+
     // for debugging
     std::string str() const;