refactor: Focus speculators Eagle support on V1 engine only

- Remove V0 engine changes from eagle.py
- Keep V1 engine support in llama_eagle.py with layernorm support
- Maintain config detection and translation for speculators format
- Ensure V1 engine compatibility for all Eagle models

This simplifies the implementation by focusing only on the modern V1 engine
which provides better performance and features.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
Signed-off-by: Rahul Tuli <rtuli@redhat.com>

Author: rahul-tuli

vllm/model_executor/models/eagle.py

@@ -204,24 +204,8 @@ def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]):
         # https://huggingface.co/abhigoyal/EAGLE-LLaMA3-Instruct-8B-vllm
         # Also, here's an example script for converting trained EAGLE
         # checkpoint to vLLM compatible version: https://gist.github.com/abhigoyal1997/1e7a4109ccb7704fbc67f625e86b2d6d
-        
-        # Support for speculators format weights
-        speculators_name_map = {
-            "fusion_fc.weight": "fc.weight",
-            "fusion_fc.bias": "fc.bias",
-            "embedding_layernorm.weight": "enorm.weight",
-            "pre_lm_head_layernorm.weight": "hnorm.weight",
-        }
-        
         model_weights = {}
         for name, loaded_weight in weights:
-            # Handle speculators format weight names
-            if name in speculators_name_map:
-                name = speculators_name_map[name]
-            elif name.startswith("transformer."):
-                # transformer.* -> model.model.layers.0.*
-                suffix = name[len("transformer."):]
-                name = f"model.model.layers.0.{suffix}"
             if name == "token_map":
                 if self.config.truncated_vocab_size < self.config.vocab_size:
                     self.token_map = nn.Parameter(loaded_weight,