[V1][Spec Decode] Respect prompt_lookup_max (#15348)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

tests/v1/spec_decode/test_ngram.py

@@ -2,7 +2,8 @@
 
 import numpy as np
 
-from vllm.v1.spec_decode.ngram_proposer import (_find_subarray_kmp,
+from vllm.v1.spec_decode.ngram_proposer import (NgramProposer,
+                                                _find_subarray_kmp,
                                                 _kmp_lps_array)
 
 
@@ -35,3 +36,53 @@ def test_find_subarray_kmp():
     # Return on the first match
     np.testing.assert_array_equal(_find_subarray_kmp(X, 1, 3),
                                   np.array([6, 2, 3]))
+
+
+def test_ngram_proposer():
+    proposer = NgramProposer()
+
+    # No match.
+    result = proposer.propose(
+        context_token_ids=np.array([1, 2, 3, 4, 5]),
+        min_n=2,
+        max_n=2,
+        k=2,
+    )
+    assert result is None
+
+    # No match for 4-gram.
+    result = proposer.propose(
+        context_token_ids=np.array([1, 2, 3, 4, 1, 2, 3]),
+        min_n=4,
+        max_n=4,
+        k=2,
+    )
+    assert result is None
+
+    # No match for 4-gram but match for 3-gram.
+    result = proposer.propose(
+        context_token_ids=np.array([1, 2, 3, 4, 1, 2, 3]),
+        min_n=3,
+        max_n=4,
+        k=2,
+    )
+    assert np.array_equal(result, np.array([4, 1]))
+
+    # Match for both 4-gram and 3-gram.
+    # In this case, the proposer should return the 4-gram match.
+    result = proposer.propose(
+        context_token_ids=np.array([2, 3, 4, 5, 1, 2, 3, 4, 1, 2, 3, 4]),
+        min_n=3,
+        max_n=4,
+        k=2,
+    )
+    assert np.array_equal(result, np.array([1, 2]))  # Not [5, 1]
+
+    # Match for 2-gram and 3-gram, but not 4-gram.
+    result = proposer.propose(
+        context_token_ids=np.array([3, 4, 5, 2, 3, 4, 1, 2, 3, 4]),
+        min_n=2,
+        max_n=4,
+        k=2,
+    )
+    assert np.array_equal(result, np.array([1, 2]))  # Not [5, 2]