Add MTP decoding support for GLM-4.x MoE (#1270)

* wip: port MTP architecture

Ports the Multi-Token Prediction (MTP) architecture to the older `llama.cpp` codebase used by `ikllama`.

Changes include:
- Updating `llama_batch` to support `mtp_params`.
- Modifying `llama_decode_internal` (and `encode`) to handle MTP operations (Warmup, Update, Draft).
- Adding public APIs for MTP state management (`llama_set_draft_input_hidden_state`).
- Adapting the embedding extraction logic to skip MTP update passes.

* Refactors `server_slot` to support generic speculative decoding (MTP or Draft Model).

* core: enable hybrid outputs (logits + embeddings) for MTP support

* fix(mtp): correct KV-cache slot finding for updates

* fix(mtp): persist hidden states to prevent context corruption during drafting

* refactor(mtp): clean unused code

* fix(mtp): update server to new functions name

* fix(mtp): fix graph and save hidden state

* mtp: refactor integration, context params and kv cache search

* mtp: fix hidden state extraction and speculative acceptance flow

* server: fix MTP warmup for long prompts and reset token buffer

* llama: refactor MTP operation state to context parameters

* server: fix n_past calculation in MTP acceptance

* llama: fix mtp enable flags

* speculative: refactor MTP to use common_speculative interface

* context: remove unused signatures

* clip: fix deprecated enum-enum conversion warning

* common: fix format string crash in help message

* context: fix mtp activation logic

common/common.h

@@ -139,6 +139,7 @@ thinking_tokens thinking_tokens_from_string(const std::string& format);
 enum common_speculative_type {
     COMMON_SPECULATIVE_TYPE_NONE,          // no speculative decoding
     COMMON_SPECULATIVE_TYPE_DRAFT,         // draft model
+    COMMON_SPECULATIVE_TYPE_MTP,           // MTP model 
     COMMON_SPECULATIVE_TYPE_EAGLE3,        // eagle draft model
     COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE,  // simple self-speculative decoding
     COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K,   // self-speculative decoding with n-gram keys only
@@ -356,6 +357,7 @@ struct gpt_params {
     bool split_mode_graph_scheduling = false; // if true, force split mode graph scheduling
     //bool split_mode_f16    = true;  // if true, intermediate results will be cast to f16 before copying to other GPUs to perform reduce ops
     bool scheduler_async   = false; // if true, in split mode graph the scheduler will use multiple threads to evaluate the graph
+    bool has_mtp           = false; // enable MTP if supported by the model
 
     std::string cache_type_k = "f16"; // KV cache data type for the K
     std::string cache_type_v = "f16"; // KV cache data type for the V