diff --git a/llm_server/llm/vllm/tokenize.py b/llm_server/llm/vllm/tokenize.py index d32eb68..0a2f5c6 100644 --- a/llm_server/llm/vllm/tokenize.py +++ b/llm_server/llm/vllm/tokenize.py @@ -22,8 +22,8 @@ def tokenize(prompt: str, backend_url: str) -> int: tokenizer = tiktoken.get_encoding("cl100k_base") - # Split the prompt into 1000 character chunks - chunk_size = 1000 + # Split the prompt into 2000 character chunks + chunk_size = 2000 chunks = [prompt[i:i + chunk_size] for i in range(0, len(prompt), chunk_size)] # Define a function to send a chunk to the server