[V0 Deprecation] Remove unused swap_space parameter (#36216)

Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: mcelrath

vllm/engine/arg_utils.py

@@ -447,7 +447,6 @@ class EngineArgs:
     )
     disable_sliding_window: bool = ModelConfig.disable_sliding_window
     disable_cascade_attn: bool = ModelConfig.disable_cascade_attn
-    swap_space: float = CacheConfig.swap_space
     offload_backend: str = OffloadConfig.offload_backend
     cpu_offload_gb: float = UVAOffloadConfig.cpu_offload_gb
     cpu_offload_params: set[str] = get_field(UVAOffloadConfig, "cpu_offload_params")
@@ -961,7 +960,6 @@ class EngineArgs:
         cache_group.add_argument(
             "--kv-cache-memory-bytes", **cache_kwargs["kv_cache_memory_bytes"]
         )
-        cache_group.add_argument("--swap-space", **cache_kwargs["swap_space"])
         cache_group.add_argument("--kv-cache-dtype", **cache_kwargs["cache_dtype"])
         cache_group.add_argument(
             "--num-gpu-blocks-override", **cache_kwargs["num_gpu_blocks_override"]
@@ -1526,7 +1524,6 @@ class EngineArgs:
             block_size=self.block_size,
             gpu_memory_utilization=self.gpu_memory_utilization,
             kv_cache_memory_bytes=self.kv_cache_memory_bytes,
-            swap_space=self.swap_space,
             cache_dtype=resolved_cache_dtype,  # type: ignore[arg-type]
             is_attention_free=model_config.is_attention_free,
             num_gpu_blocks_override=self.num_gpu_blocks_override,

vllm/entrypoints/llm.py

@@ -164,12 +164,6 @@ class LLM:
             compared with using gpu_memory_utilization. Note that
             kv_cache_memory_bytes (when not-None) ignores
             gpu_memory_utilization
-        swap_space: The size (GiB) of CPU memory per GPU to use as swap space.
-            This can be used for temporarily storing the states of the requests
-            when their `best_of` sampling parameters are larger than 1. If all
-            requests will have `best_of=1`, you can safely set this to 0.
-            Noting that `best_of` is only supported in V0. Otherwise, too small
-            values may cause out-of-memory (OOM) errors.
         cpu_offload_gb: The size (GiB) of CPU memory to use for offloading
             the model weights. This virtually increases the GPU memory space
             you can use to hold the model weights, at the cost of CPU-GPU data
@@ -240,7 +234,6 @@ class LLM:
         chat_template: Path | str | None = None,
         seed: int = 0,
         gpu_memory_utilization: float = 0.9,
-        swap_space: float = 4,
         cpu_offload_gb: float = 0,
         offload_group_size: int = 0,
         offload_num_in_group: int = 1,
@@ -265,6 +258,17 @@ class LLM:
     ) -> None:
         """LLM constructor."""
 
+        if "swap_space" in kwargs:
+            kwargs.pop("swap_space")
+            import warnings
+
+            warnings.warn(
+                "The 'swap_space' parameter is deprecated and ignored. "
+                "It will be removed in a future version.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         if "disable_log_stats" not in kwargs:
             kwargs["disable_log_stats"] = True
 
@@ -353,7 +357,6 @@ class LLM:
             seed=seed,
             gpu_memory_utilization=gpu_memory_utilization,
             kv_cache_memory_bytes=kv_cache_memory_bytes,
-            swap_space=swap_space,
             cpu_offload_gb=cpu_offload_gb,
             offload_group_size=offload_group_size,
             offload_num_in_group=offload_num_in_group,