sleep model support (#3135)

Co-authored-by: salman <salman.mohammadi@outlook.com>

src/axolotl/core/trainers/grpo/__init__.py

@@ -52,6 +52,7 @@ class GRPOStrategy:
             if trl.vllm_mode:
                 grpo_args_kwargs["vllm_mode"] = trl.vllm_mode
             if trl.vllm_mode == "colocate":
+                grpo_args_kwargs["enable_sleep_mode"] = trl.vllm_enable_sleep_mode  # type: ignore[attr-defined]
                 grpo_args_kwargs["vllm_gpu_memory_utilization"] = (
                     vllm_cfg.gpu_memory_utilization
                 )

src/axolotl/utils/schemas/trl.py

@@ -167,3 +167,9 @@ class TRLConfig(BaseModel):
             "description": "Whether to exclude truncated completions from loss calculation."
         },
     )
+    vllm_enable_sleep_mode: bool | None = Field(
+        default=None,
+        json_schema_extra={
+            "description": "Enable sleep mode for vLLM to offload VRAM when idle"
+        },
+    )