Skip to content
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion tests/v1/e2e/test_spec_decode.py
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,8 @@ def test_ngram_correctness(

@pytest.mark.parametrize(
["model_setup", "mm_enabled"], [
(("eagle3", "Qwen/Qwen3-8B",
"AngelSlim/Qwen3-8B_eagle3", 1), False),
(("eagle", "meta-llama/Llama-3.1-8B-Instruct",
"yuhuili/EAGLE-LLaMA3.1-Instruct-8B", 1), False),
(("eagle3", "meta-llama/Llama-3.1-8B-Instruct",
Expand All @@ -140,7 +142,7 @@ def test_ngram_correctness(
True,
marks=pytest.mark.skip(reason="Skipping due to CI OOM issues")),
],
ids=["llama3_eagle", "llama3_eagle3", "llama4_eagle", "llama4_eagle_mm"])
ids=["qwen3_eagle3", "llama3_eagle", "llama3_eagle3", "llama4_eagle", "llama4_eagle_mm"])
def test_eagle_correctness(
monkeypatch: pytest.MonkeyPatch,
sampling_config: SamplingParams,
Expand Down
8 changes: 1 addition & 7 deletions vllm/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -3224,13 +3224,7 @@ def _verify_args(self) -> Self:
"speculative decoding is > 1, but got "
f"{self.disable_by_batch_size=}")

from vllm.transformers_utils.configs import SpeculatorsConfig

eagle3_target_supported = ["llama"]
if self.draft_model_config and isinstance(
self.draft_model_config.hf_config, SpeculatorsConfig):
eagle3_target_supported.append("qwen")

eagle3_target_supported = ["llama", "qwen"]
if self.method == "eagle3" and self.target_model_config and not any(
supported_model in
self.target_model_config.hf_text_config.model_type
Expand Down
Loading