server : support multi-modal context checkpoints (#19849)

* Modify llama-memory-hybrid-iswa.cpp

* Modify llama-memory-recurrent.cpp

* Modify server-common.cpp

* Modify server-common.h

* Modify server-context.cpp

* Modify server-task.h

* Added comment to llama-memory-hybrid-iswa.cpp

* Remove comment from server-context.cpp

* Stylistic fix server-context.cpp

* Fix an issue when seqrm isn't called in server-context.cpp

* cont : alternative impl

* cont : cleanup

* cont : n_tokens -> int64_t

---------

Co-authored-by: timkhronos <timkhronos@gmail.com>

tools/server/server-common.h

@@ -167,7 +167,12 @@ public:
     // for debugging
     std::string str() const;
 
-    llama_pos pos_next() const;
+    // the next position after n_tokens. if n_tokens < 0, return the next position after all tokens.
+    llama_pos pos_next(int64_t n_tokens = -1) const;
+
+    // number of tokens with position <= max_pos
+    size_t size_up_to_pos(llama_pos max_pos) const;
+
     const mtmd::input_chunk_ptr & find_chunk(size_t idx) const;
 
     void push_back(llama_token tok);