Merge pull request #227 from hrz6976/main

Add a lock to server inference()

ktransformers/server/backend/interfaces/ktransformers.py

 import torch
+import asyncio
 from transformers import AutoTokenizer, AutoConfig, GenerationConfig
 from ktransformers.server.backend.interfaces.transformers import (
     TransformersInterface,
@@ -70,6 +71,8 @@ class KTransformersInterface(TransformersInterface):
             self.model.generation_config.pad_token_id = self.model.generation_config.eos_token_id
         self.streamer = TextStreamer(self.tokenizer)
 
+        self._infer_lock = asyncio.Lock()
+
     def decode_one_tokens(self):
         device_map = self.model.gguf_loader.tensor_device_map
         torch_device = get_device("blk.0.self_attn", device_map)
@@ -171,4 +174,9 @@ class KTransformersInterface(TransformersInterface):
     @property
     def active_cache_position(self):
         device = self.device_map.get("blk.0.self_attn", {}).get("generate_device", "cuda:0")
-        return torch.tensor([self.seq_length - 1], device=device)
+        return torch.tensor([self.seq_length - 1], device=device)
\ No newline at end of file
+    
+    async def inference(self, local_messages, thread_id: str):
+        async with self._infer_lock:
+            async for v in super().inference(local_messages, thread_id):
+                yield v
\ No newline at end of file