[Guards] The draft guard reports the draft model's own architecture

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-09 19:55:23 +07:00
co-authored by Hinata
parent 09ea3a66e9
commit 54d4ab1b9a
+17 -3
View File
@@ -100,9 +100,23 @@ def _name(value) -> str:
return getattr(value, "name", str(value))
def _profile(vllm_config) -> tuple[list[str], object, object, list[str] | None]:
"""Resolved (architectures, mode, cudagraph mode, splitting ops)."""
def _profile(
vllm_config, role: str = "target"
) -> tuple[list[str], object, object, list[str] | None]:
"""Resolved (architectures, mode, cudagraph mode, splitting ops).
For ``role="draft"`` the architectures are the DRAFT model's
(``speculative_config.draft_model_config``): the drafter is constructed
with the target's VllmConfig, whose model_config names the target. The reference host
logged the target architecture on the draft line before this fix.
The graph profile is the engine's single CompilationConfig for both roles.
"""
model_config = getattr(vllm_config, "model_config", None)
if role == "draft":
spec = getattr(vllm_config, "speculative_config", None)
draft_config = getattr(spec, "draft_model_config", None)
if draft_config is not None:
model_config = draft_config
if model_config is None:
raise RuntimeError("e2-guard: vllm_config has no model_config to check")
compilation_config = getattr(vllm_config, "compilation_config", None)
@@ -137,7 +151,7 @@ def assert_graph_profile_is_executable(vllm_config, *, role: str = "target") ->
``Qwen4ExpMTP`` builds ``Qwen4ExpMultiTokenPredictor`` rather than
``Qwen4ExpForCausalLM``, from a config rebuilt in ``mtp.py``.
"""
architectures, mode, cudagraph_mode, splitting_ops = _profile(vllm_config)
architectures, mode, cudagraph_mode, splitting_ops = _profile(vllm_config, role)
detail = (
f"architectures={architectures} breakable={os.environ.get(BREAKABLE_ENV)} "
f"compilation_mode={_name(mode)} cudagraph_mode={_name(cudagraph_mode)}"