fix for intel devices torch compile configs (#3952)

* fix for intel devices

* Refactor torch_compile_options to use base options with device-specific extensions

- Extract common options into base_options shared by all device types
- CUDA devices get additional CUDA-specific options
- XPU, HIP, and other devices use base options only
- Reduces code duplication and improves maintainability

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: danielhanchen <danielhanchen@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

unsloth/models/rl.py

@@ -26,6 +26,7 @@ from unsloth_zoo.compiler import create_new_function
 from unsloth_zoo.log import logger
 from unsloth_zoo.logging_utils import PatchRLStatistics
 from unsloth_zoo.rl_replacements import RL_REPLACEMENTS
+from ..device_type import DEVICE_TYPE
 from .rl_replacements import (
     RL_EXTRA_ARGS,
     RL_FUNCTIONS,
@@ -251,6 +252,7 @@ from torch.nn import functional as F
 import inspect
 from transformers import DataCollatorForSeq2Seq, DataCollatorForLanguageModeling as TransformersDataCollatorForLanguageModeling
 from transformers.training_args import ParallelMode
+from unsloth_zoo.device_type import DEVICE_TYPE, device_synchronize
 
 # Wrap trainer with padding to right and enable training mode
 # Also patches W&B since multiple runs must use wandb.finish()
@@ -1091,18 +1093,33 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
     )
 
     if RLTrainer_name == "GRPOTrainer":
-        new_options = """torch_compile_options = {
+        # Base torch_compile_options shared by all device types
+        base_options = """torch_compile_options = {
             "epilogue_fusion"   : True,
             "max_autotune"      : False,
             "shape_padding"     : True,
-            "trace.enabled"     : False,
-            #"combo_kernels"     : torch.cuda.get_device_capability()[0] >= 10,
+            "trace.enabled"     : False,"""
+
+        # Generate torch_compile_options based on device type
+        if DEVICE_TYPE == "cuda":
+            # CUDA-specific options (added to base options)
+            new_options = (
+                base_options
+                + """
             "triton.enable_persistent_tma_matmul": torch.cuda.get_device_capability()[0] >= 9,
-            "cuda.cutlass_epilogue_fusion_enabled": torch.cuda.get_device_capability()[0] >= 9, 
-            "cuda.cutlass_tma_only": torch.cuda.get_device_capability()[0] >= 9, 
+            "cuda.cutlass_epilogue_fusion_enabled": torch.cuda.get_device_capability()[0] >= 9,
+            "cuda.cutlass_tma_only": torch.cuda.get_device_capability()[0] >= 9,
             "cuda.compile_opt_level"              : "-O2",
             "cuda.enable_cuda_lto"                : True,
         }"""
+            )
+        else:
+            # XPU, HIP, and other device types use base options only
+            new_options = (
+                base_options
+                + """
+        }"""
+            )
 
         pattern = r"torch_compile_options\s*=\s*\{[^}]*\}"
 

unsloth/models/rl_replacements.py

@@ -29,6 +29,7 @@ from unsloth_zoo.rl_replacements import RL_REPLACEMENTS, left_pack_padding
 from unsloth_zoo.utils import Version
 from importlib.metadata import version as importlib_version
 from unsloth_zoo.log import logger
+from unsloth_zoo.device_type import device_synchronize
 import importlib.util
 from ..device_type import (
     is_hip,
@@ -781,7 +782,7 @@ def grpo_trainer__get_per_token_logps_and_entropies(function_name, function):
                         )
                     # This is needed to avoid race conditions with GPT OSS offload_embbed=True
                     # However, it seems that this line does not slow down or disrupt models.
-                    torch.cuda.synchronize()
+                    device_synchronize()
                     all_logprobs_list.append(logprobs_chunk)
                 logprobs = torch.cat(all_logprobs_list, dim = 0)
                 entropies = None