Supports multiple input suffixes for global_segment_size

Author: Liziqi-77

examples/disaggregated_prefill_v1/mooncake_connector_store_deployment_guide.md

@@ -24,7 +24,7 @@ The environment variable **MOONCAKE_CONFIG_PATH** is configured to the full path
     "protocol": "ascend",
     "device_name": "",
     "master_server_address": "xx.xx.xx.xx:50088",
-    "global_segment_size": 30000000000
+    "global_segment_size": "1GB/1024MB/1048576KB/1073741824B" or 1073741824
 }
 ```
 

vllm_ascend/distributed/mooncake/config_data.py

@@ -11,6 +11,8 @@
 from vllm.utils import cdiv, logger
 from vllm.v1.core.sched.output import NewRequestData
 
+DEFAULT_GLOBAL_SEGMENT_SIZE = 3355443200  # 3.125 GiB
+DEFAULT_LOCAL_BUFFER_SIZE = 1073741824  # 1.0 GiB
 
 @dataclass
 class MooncakeEngineMetadata:
@@ -419,7 +421,7 @@ class LasyerMultiBlockReqMeta:
 class MooncakeStoreConfig:
     local_hostname: str
     metadata_server: str
-    global_segment_size: int
+    global_segment_size: int | str
     local_buffer_size: int
     protocol: str
     device_name: str
@@ -433,8 +435,12 @@ def from_file(file_path: str) -> "MooncakeStoreConfig":
         return MooncakeStoreConfig(
             local_hostname=config.get("local_hostname"),
             metadata_server=config.get("metadata_server"),
-            global_segment_size=config.get("global_segment_size", 3355443200),
-            local_buffer_size=config.get("local_buffer_size", 1073741824),
+            global_segment_size=_parse_global_segment_size(
+                config.get("global_segment_size", DEFAULT_GLOBAL_SEGMENT_SIZE)
+            ),
+            local_buffer_size=_parse_global_segment_size(
+                config.get("local_buffer_size", DEFAULT_LOCAL_BUFFER_SIZE)
+            ),
             protocol=config.get("protocol", "tcp"),
             device_name=config.get("device_name", ""),
             master_server_address=config.get("master_server_address"),
@@ -446,4 +452,75 @@ def load_from_env() -> "MooncakeStoreConfig":
         if not config_path:
             raise ValueError(
                 "The environment variable 'MOONCAKE_CONFIG_PATH' is not set.")
-        return MooncakeStoreConfig.from_file(config_path)
+        return MooncakeStoreConfig.from_file(config_path)
+
+
+def _parse_global_segment_size(value) -> int:
+    """
+    Parse storage size strings with support for units: GB, MB, KB, B
+    
+    Args:
+        value: Input value (int, str, or other convertible types)
+        
+    Returns:
+        int: Size in bytes
+        
+    Raises:
+        ValueError: For invalid format, missing number, or negative values
+        TypeError: For unsupported input types
+    """
+
+    if isinstance(value, int):
+        return value
+    elif not isinstance(value, str):
+        try:
+            return int(value)
+        except (TypeError, ValueError) as e:
+            raise TypeError(f"Unsupported type for global_segment_size: {type(value)}") from e
+    # Clean input string
+    cleaned_input = value.strip().lower()
+    if not cleaned_input:
+        raise ValueError("global segment size cannot be empty.")
+
+    UNIT_MULTIPLIERS  = {
+        'gb': 1024 ** 3,  # 1 GB = 1024^3 bytes
+        'mb': 1024 ** 2,  # 1 MB = 1024^2 bytes
+        'kb': 1024,       # 1 KB = 1024 bytes
+        'b': 1            # 1 B = 1 byte
+    }
+    # Check for unit suffixes
+    for unit, multiplier in UNIT_MULTIPLIERS.items():
+        if cleaned_input.endswith(unit):
+            number_part = cleaned_input[:-len(unit)].strip()
+            if not number_part:
+                raise ValueError(f"Missing numeric value before unit '{unit}' in: '{value}'")
+            return _convert_to_bytes(number_part, multiplier, value)
+    # Handle unit-less input (bytes)
+    return _convert_to_bytes(cleaned_input, 1, value)
+
+
+def _convert_to_bytes(number_str: str, multiplier: int, original_input: str) -> int:
+    """
+    Convert numeric string to byte count
+    
+    Args:
+        number_str: Numeric portion of input
+        multiplier: Unit conversion factor
+        original_input: Original input string (for error messages)
+        
+    Returns:
+        int: Byte count
+        
+    Raises:
+        ValueError: For invalid numbers or negative results
+    """
+    try:
+        numeric_value = float(number_str)
+    except ValueError:
+        raise ValueError(f"Invalid numeric value '{number_str}' in: '{original_input}'")
+    # Calculate byte count
+    try:
+        byte_count = int(numeric_value * multiplier)
+    except OverflowError:
+        raise ValueError(f"Storage size too large: '{original_input}'")
+    return byte_count