[Refactor][EAGLE] 8/N delete mtp_proposer (#7016)

### What this PR does / why we need it?
This PR aims to delete mtp_proposer. By fixing a bug in both dsv32 and
glm5, now it should be ok to remove mtp_proposer. The bug is actually
about unnecessary slicing of `slot_mapping`.

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
by ci

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: Zetong Li <slippersss@126.com>

vllm_ascend/spec_decode/__init__.py

@@ -18,7 +18,6 @@
 #
 from vllm_ascend.spec_decode.eagle_proposer import AscendEagleProposer
 from vllm_ascend.spec_decode.medusa_proposer import AscendMedusaProposer
-from vllm_ascend.spec_decode.mtp_proposer import AscendMtpProposer
 from vllm_ascend.spec_decode.ngram_proposer import AscendNgramProposer
 from vllm_ascend.spec_decode.suffix_proposer import AscendSuffixDecodingProposer
 
@@ -30,9 +29,7 @@ def get_spec_decode_method(method, vllm_config, device, runner):
         return AscendSuffixDecodingProposer(vllm_config, runner)
     elif method == "medusa":
         return AscendMedusaProposer(vllm_config, device)
-    elif method in ("eagle", "eagle3"):
+    elif method in ("eagle", "eagle3", "mtp"):
         return AscendEagleProposer(vllm_config, device, runner)
-    elif method == "mtp":
-        return AscendMtpProposer(vllm_config, device, runner)
     else:
         raise ValueError(f"Unknown speculative decoding method: {method}")