[Spec Decode] Remove Medusa and MLP speculator support (#61701)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Woosuk Kwon
2026-10-14 17:29:23 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 273a04964e
commit 8530aed2b7
27 changed files with 27 additions and 885 deletions
@@ -1,21 +1,4 @@
{
"abhigoyal/vllm-medusa-llama-68m-random": {
"architectures": [
"MedusaModel"
],
"model_type": "medusa",
"text_model_type": "medusa",
"hidden_size": 768,
"total_num_hidden_layers": 1,
"total_num_attention_heads": 0,
"head_size": "Error: integer division or modulo by zero",
"vocab_size": 32000,
"total_num_kv_heads": 0,
"num_experts": 0,
"is_deepseek_mla": false,
"is_multimodal_model": false,
"dtype": "torch.float32"
},
"luccafong/deepseek_mtp_draft_random": {
"architectures": [
"DeepSeekMTPModel"
+6 -21
View File
@@ -55,7 +55,6 @@ BASE_MODELS_TO_TEST = [
# (target_model, draft_model, trust_remote_code)
SPECULATIVE_MODELS = [
("JackFram/llama-68m", "abhigoyal/vllm-medusa-llama-68m-random", False),
("luccafong/deepseek_mtp_main_random", "luccafong/deepseek_mtp_draft_random", True),
("eagle618/deepseek-v3-random", "eagle618/eagle-deepseek-v3-random", True),
("meta-llama/Meta-Llama-3-8B-Instruct", "yuhuili/EAGLE-LLaMA3-Instruct-8B", True),
@@ -136,9 +135,7 @@ def test_qwen35_decision_config_selects_d3(tmp_path, has_decision_config, archit
assert not hasattr(config, "decision_config")
def _assert_model_arch_config(
model_config, expected: dict, check_head_size: bool = True
):
def _assert_model_arch_config(model_config, expected: dict):
"""Assert model_arch_config matches expected values."""
model_arch_config = model_config.model_arch_config
assert model_arch_config.architectures == expected["architectures"]
@@ -164,14 +161,10 @@ def _assert_model_arch_config(
config_format="hf",
)
assert str(torch_dtype) == expected["dtype"]
if check_head_size:
assert model_arch_config.head_size == expected["head_size"]
assert model_arch_config.head_size == expected["head_size"]
def _assert_model_config_methods(
model_config, expected: dict, check_head_size: bool = True
):
def _assert_model_config_methods(model_config, expected: dict):
"""Assert model_config methods return expected values."""
assert model_config.architectures == expected["architectures"]
assert model_config.get_vocab_size() == expected["vocab_size"]
@@ -182,9 +175,7 @@ def _assert_model_config_methods(
model_config.get_total_num_hidden_layers()
== expected["total_num_hidden_layers"]
)
if check_head_size:
assert model_config.get_head_size() == expected["head_size"]
assert model_config.get_head_size() == expected["head_size"]
def test_head_size_falls_back_when_head_dim_is_zero():
@@ -519,14 +510,8 @@ def test_draft_model_arch_config(
)
model_config = speculative_config.draft_model_config
# For medusa models, head_size may cause division by zero before
# model_arch_config was introduced, so we conditionally check it
check_head_size = isinstance(expected["head_size"], int)
_assert_model_arch_config(model_config, expected, check_head_size=check_head_size)
_assert_model_config_methods(
model_config, expected, check_head_size=check_head_size
)
_assert_model_arch_config(model_config, expected)
_assert_model_config_methods(model_config, expected)
def test_deepseek_v4_convertor_splits_vision_architecture():