draft-trunc guard: v0.31.0 is a release build (bare version string, no +g<sha> scm suffix) — pin the guard to the release version, keep the fail-loud semantics

docker-images/glm53-kindling/experimental/draft-trunc/draft_trunc.py

@@ -27,10 +27,12 @@ import vllm
 from vllm.triton_utils import tl, triton
 
 # The other files in this directory are whole copies of vLLM's, with the cut added. They
-# match one vLLM commit, the image's VLLM_REF. On any other they would put back old code
+# match one vLLM version, the image's VLLM_REF. On any other they would put back old code
 # over new, so the engine stops instead.
-VLLM_COMMIT = "ddd6fbca"
-if f"+g{VLLM_COMMIT}" not in vllm.__version__:
+# The v0.31.0 base is a RELEASE build: its version string is the bare "0.31.0"
+# (the nightly bases carried a +g<sha> scm suffix, e.g. +gddd6fbca).
+VLLM_COMMIT = "0.31.0"  # v0.31.0 release (tag commit db9527a4)
+if vllm.__version__ != VLLM_COMMIT:
     raise RuntimeError(f"experimental/draft-trunc copies vLLM {VLLM_COMMIT}'s files, but this image runs "
                        f"vLLM {vllm.__version__}. Refresh the copies from this image, or remove the "
                        "draft-trunc mounts from experimental/compose/adaptive-k.yaml.")