Merge pull request #3843 from unslothai/fix-grpo-version-compat

Unify Version usage and fix TRL version handling

unsloth/kernels/cross_entropy_loss.py

@@ -24,7 +24,7 @@ from .utils import (
     is_cdna,
 )
 from transformers.models.llama.modeling_llama import logger
-from packaging.version import Version
+from unsloth_zoo.utils import Version
 
 from unsloth_zoo.loss_utils import (
     patch_loss_functions as _patch_loss_functions,

unsloth/models/cohere.py

@@ -15,7 +15,7 @@
 from .llama import *
 from ._utils import __version__
 from unsloth_zoo.hf_utils import dtype_from_config
-from unsloth_zoo.utils import _get_dtype
+from unsloth_zoo.utils import _get_dtype, Version
 from ..utils.packing import get_packed_info_from_kwargs
 from ..utils.attention_dispatch import (
     AttentionConfig,
@@ -35,8 +35,6 @@ try:
         repeat_kv,
     )
 except:
-    from packaging.version import Version
-
     transformers_version = Version(transformers_version)
     if not transformers_version >= Version("4.42"):
         raise ImportError(

unsloth/models/gemma.py

@@ -14,7 +14,7 @@
 
 from .llama import *
 from ._utils import __version__
-from unsloth_zoo.utils import _get_dtype
+from unsloth_zoo.utils import _get_dtype, Version
 from unsloth_zoo.hf_utils import dtype_from_config
 from ..utils.packing import (
     build_sdpa_packed_attention_mask,
@@ -34,8 +34,6 @@ try:
         repeat_kv,
     )
 except:
-    from packaging.version import Version
-
     transformers_version = Version(transformers_version)
     if not transformers_version >= Version("4.38"):
         raise ImportError(

unsloth/models/gemma2.py

@@ -14,7 +14,7 @@
 
 from .llama import *
 from ._utils import __version__
-from unsloth_zoo.utils import _get_dtype
+from unsloth_zoo.utils import _get_dtype, Version
 from unsloth_zoo.hf_utils import dtype_from_config
 from ..utils.packing import get_packed_info_from_kwargs
 from ..utils.attention_dispatch import (
@@ -41,8 +41,6 @@ try:
         repeat_kv,
     )
 except:
-    from packaging.version import Version
-
     transformers_version = Version(transformers_version)
     if not transformers_version >= Version("4.42"):
         raise ImportError(

unsloth/models/granite.py

@@ -15,7 +15,7 @@
 from .llama import *
 import os
 from ._utils import __version__
-from unsloth_zoo.utils import _get_dtype
+from unsloth_zoo.utils import _get_dtype, Version
 from unsloth_zoo.hf_utils import dtype_from_config
 from ..utils.packing import get_packed_info_from_kwargs
 from ..utils.attention_dispatch import (
@@ -41,8 +41,6 @@ try:
         GraniteForCausalLM,
     )
 except:
-    from packaging.version import Version
-
     transformers_version = Version(transformers_version)
     if not transformers_version >= Version("4.45.0"):
         raise ImportError(

unsloth/models/loader_utils.py

@@ -28,7 +28,6 @@ from .mapper import (
 )
 
 # https://github.com/huggingface/transformers/pull/26037 allows 4 bit loading!
-from packaging.version import Version
 from transformers import __version__ as transformers_version
 from unsloth.models._utils import TorchAOConfig
 from unsloth_zoo.utils import Version

unsloth/models/rl.py

@@ -43,10 +43,31 @@ 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):

unsloth/trainer.py

@@ -211,7 +211,7 @@ def _backwards_compatible_trainer(trainer_class, config_class):
         if "processing_class" in trainer_params and "tokenizer" in kwargs:
             kwargs["processing_class"] = kwargs.pop("tokenizer")
 
-        if ("args" in kwargs) and (Version(trl.__version__) >= Version("0.13.0.dev0")):
+        if ("args" in kwargs) and (Version(trl) >= Version("0.13.0.dev0")):
             training_args = kwargs.pop("args", None)
 
             # Get parameters that Trainer.__init__ actually expects
@@ -412,7 +412,7 @@ def _patch_trl_trainer():
 
     if hasattr(trl, "__UNSLOTH_BACKWARDS_COMPATIBLE__"):
         return
-    if Version(trl.__version__) <= Version("0.11.0"):
+    if Version(trl) <= Version("0.11.0"):
         return
 
     import trl.trainer