Improve docs (#17)

python/sglang/lang/interpreter.py

@@ -632,11 +632,7 @@ class ProgramState:
         self.stream_executor.end()
 
     def __repr__(self) -> str:
-        msgs = self.messages()
-        ret = ""
-        for msg in msgs:
-            ret += msg["role"] + ":\n" + msg["content"] + "\n"
-        return ret
+        return f"ProgramState({self.text()})"
 
 
 class ProgramStateGroup:

python/sglang/srt/layers/context_flashattention_nopad.py

@@ -5,7 +5,6 @@ import triton
 import triton.language as tl
 from sglang.srt.utils import wrap_kernel_launcher
 
-
 CUDA_CAPABILITY = torch.cuda.get_device_capability()
 
 

python/sglang/srt/layers/extend_attention.py

@@ -4,7 +4,6 @@ import triton.language as tl
 from sglang.srt.layers.context_flashattention_nopad import context_attention_fwd
 from sglang.srt.utils import wrap_kernel_launcher
 
-
 CUDA_CAPABILITY = torch.cuda.get_device_capability()
 
 

python/sglang/srt/managers/router/model_rpc.py

@@ -2,10 +2,10 @@ import asyncio
 import logging
 import multiprocessing
 import time
+import warnings
 from concurrent.futures import ThreadPoolExecutor
 from enum import Enum, auto
 from typing import Dict, List, Optional, Tuple, Union
-import warnings
 
 import numpy as np
 import rpyc