Format code (#118)

README.md

@@ -324,7 +324,7 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
 - Mixtral
 - LLaVA
   - `python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.5-7b --tokenizer-path llava-hf/llava-1.5-7b-hf --port 30000`
-- Qwen
+- Qwen / Qwen 2
 - AWQ quantization
 
 ## Benchmark And Performance

python/sglang/srt/models/llama2.py

@@ -319,4 +319,5 @@ class LlamaForCausalLM(nn.Module):
                 weight_loader = getattr(param, "weight_loader", default_weight_loader)
                 weight_loader(param, loaded_weight)
 
+
 EntryClass = LlamaForCausalLM

python/sglang/srt/models/llava.py

@@ -331,4 +331,5 @@ def monkey_path_clip_vision_embed_forward():
         clip_vision_embed_forward,
     )
 
+
 EntryClass = LlavaLlamaForCausalLM

python/sglang/srt/models/mixtral.py

@@ -377,4 +377,5 @@ class MixtralForCausalLM(nn.Module):
                 weight_loader = getattr(param, "weight_loader", default_weight_loader)
                 weight_loader(param, loaded_weight)
 
+
 EntryClass = MixtralForCausalLM

python/sglang/srt/models/qwen.py

@@ -259,4 +259,5 @@ class QWenLMHeadModel(nn.Module):
                 weight_loader = getattr(param, "weight_loader", default_weight_loader)
                 weight_loader(param, loaded_weight)
 
+
 EntryClass = QWenLMHeadModel

python/sglang/srt/models/qwen2.py

@@ -315,4 +315,5 @@ class Qwen2ForCausalLM(nn.Module):
                 weight_loader = getattr(param, "weight_loader", default_weight_loader)
                 weight_loader(param, loaded_weight)
 
+
 EntryClass = Qwen2ForCausalLM