[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
-10
View File
@@ -1456,16 +1456,6 @@ _MULTIMODAL_EXAMPLE_MODELS = {
_SPECULATIVE_DECODING_EXAMPLE_MODELS = {
# [Medusa]
"MedusaModel": _HfExamplesInfo(
"JackFram/llama-68m", speculative_model="abhigoyal/vllm-medusa-llama-68m-random"
),
# Temporarily disabled.
# TODO(woosuk): Re-enable this once the MLP Speculator is supported in V1.
# "MLPSpeculatorPreTrainedModel": _HfExamplesInfo(
# "JackFram/llama-160m",
# speculative_model="ibm-ai-platform/llama-160m-accelerator"
# ),
# [DFlash]
"DFlashDraftModel": _HfExamplesInfo(
"Qwen/Qwen3-4B",
-3
View File
@@ -113,9 +113,6 @@ def test_registry_model_property(model_arch, is_mm, score_type):
@pytest.mark.parametrize(
"model_arch,is_pp",
[
# TODO(woosuk): Re-enable this once the MLP Speculator is supported
# in V1.
# ("MLPSpeculatorPreTrainedModel", False),
("DeepseekV2ForCausalLM", True),
("Qwen2VLForConditionalGeneration", True),
],