Set the default value of `max_context_token_num` 1 (#761)

docs/en/turbomind_config.md

@@ -28,7 +28,7 @@ rope_theta = 10000.0
 size_per_head = 128
 group_size = 0
 max_batch_size = 64
-max_context_token_num = 4
+max_context_token_num = 1
 step_length = 1
 cache_max_entry_count = 0.5
 cache_block_seq_len = 128

docs/zh_cn/turbomind_config.md

@@ -28,7 +28,7 @@ rope_theta = 10000.0
 size_per_head = 128
 group_size = 0
 max_batch_size = 64
-max_context_token_num = 4
+max_context_token_num = 1
 step_length = 1
 cache_max_entry_count = 0.5
 cache_block_seq_len = 128

lmdeploy/turbomind/deploy/target_model/base.py

@@ -48,7 +48,7 @@ class TurbomindModelConfig:
     size_per_head: int = 128
     group_size: int = 0
     max_batch_size: int = 64
-    max_context_token_num: int = 4
+    max_context_token_num: int = 1
     step_length: int = 1
     cache_max_entry_count: float = 0.5
     cache_block_seq_len: int = 128