[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726)

Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

vllm/model_executor/models/mamba2.py

@@ -228,6 +228,7 @@ class Mamba2ForCausalLM(
             head_dim=hf_config.head_dim,
             state_size=hf_config.state_size,
             conv_kernel=hf_config.conv_kernel,
+            num_spec=vllm_config.num_speculative_tokens,
         )
 
     @classmethod