From 7fd3a6c177fc242e94b16aee861bb541ae0c25c6 Mon Sep 17 00:00:00 2001
From: danielhanchen <danielhanchen@users.noreply.github.com>
Date: Mon, 5 Jan 2026 13:39:03 +0000
Subject: [PATCH] Restore TRL version fallback in rl.py

---
 unsloth/models/rl.py | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py
index fd0c69bb0e..11a5215c99 100644
--- a/unsloth/models/rl.py
+++ b/unsloth/models/rl.py
@@ -43,10 +43,28 @@ torch_compile_options = {
     "triton.cudagraphs": False,
 }
 
-from trl import __version__ as trl_version
+# vLLM compatibility shim (TRL expects GuidedDecodingParams even if vLLM doesn't provide it)
+try:
+    import vllm.sampling_params as _unsloth_vllm_sp
+    if not hasattr(_unsloth_vllm_sp, "GuidedDecodingParams"):
+        class GuidedDecodingParams:
+            def __init__(self, **kwargs):
+                self.kwargs = kwargs
+        _unsloth_vllm_sp.GuidedDecodingParams = GuidedDecodingParams
+except Exception:
+    pass
+
+from trl import __version__ as trl_version_raw
+from importlib.metadata import version as importlib_version
 from unsloth_zoo.utils import Version
 
-trl_version = Version(trl_version)
+try:
+    trl_version = Version(trl_version_raw)
+except Exception:
+    try:
+        trl_version = Version(importlib_version("trl"))
+    except Exception:
+        trl_version = Version("0.0.0")
 
 
 def vLLMSamplingParams(**kwargs):