[Cleanup] Remove obsolete spec decoding compatibility logic (#32003)

Signed-off-by: Nick Hill <nickhill123@gmail.com>

tests/v1/spec_decode/test_ngram.py

@@ -82,10 +82,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[1, 2, 3, 4, 5]])
     result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result[0]) == 0
 
@@ -93,10 +91,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[1, 2, 3, 4, 1, 2, 3]])
     result = get_ngram_proposer(min_n=4, max_n=4, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result[0]) == 0
 
@@ -104,10 +100,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[1, 2, 3, 4, 1, 2, 3]])
     result = get_ngram_proposer(min_n=3, max_n=4, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert np.array_equal(result, np.array([[4, 1]]))
 
@@ -116,10 +110,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[2, 3, 4, 5, 1, 2, 3, 4, 1, 2, 3, 4]])
     result = get_ngram_proposer(min_n=3, max_n=4, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert np.array_equal(result, np.array([[1, 2]]))  # Not [5, 1]]
 
@@ -127,10 +119,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[3, 4, 5, 2, 3, 4, 1, 2, 3, 4]])
     result = get_ngram_proposer(min_n=2, max_n=4, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert np.array_equal(result, np.array([[1, 2]]))  # Not [5, 2]]
 
@@ -138,10 +128,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[1, 2, 3, 100, 1, 2, 3, 200, 1, 2, 3, 300, 1, 2, 3]])
     result = get_ngram_proposer(min_n=3, max_n=3, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert np.array_equal(result, np.array([[100, 1]]))
 
@@ -149,10 +137,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[]])
     result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
         sampled_token_ids=[[0]],
-        req_ids=["0"],
         num_tokens_no_spec=np.array([len(c) for c in token_ids_cpu]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result[0]) == 0
 
@@ -162,10 +148,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([[1, 2, 3, 1, 2], [4, 5, 6, -1, -1]])
     result = get_ngram_proposer(min_n=2, max_n=2, k=2).propose(
         sampled_token_ids=[[0], [1]],
-        req_ids=["0", "1"],
         num_tokens_no_spec=np.array([5, 3]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result[0]) == 2
     assert np.array_equal(result[0], np.array([3, 1]))
@@ -183,10 +167,8 @@ def test_ngram_proposer():
     sampled_token_ids = [[2], [], [8]]  # Empty list for request 1 simulates prefill
     result = proposer.propose(
         sampled_token_ids=sampled_token_ids,
-        req_ids=["0", "1", "2"],
         num_tokens_no_spec=num_tokens_no_spec,
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result) == 3
     assert np.array_equal(result[0], [3, 1])
@@ -214,10 +196,8 @@ def test_ngram_proposer():
     token_ids_cpu = np.array([input_1, input_2])
     result = ngram_proposer.propose(
         sampled_token_ids=[[0], [1]],
-        req_ids=["0", "1"],
         num_tokens_no_spec=np.array([len(input_1), 3]),
         token_ids_cpu=token_ids_cpu,
-        spec_decode_unsupported_reqs=(),
     )
     assert len(result[0]) == 2
     assert np.array_equal(result[0], np.array([middle_integer + 2, middle_integer + 3]))