Commit 83d2b30d authored by Ying Sheng's avatar Ying Sheng
Browse files

format

parent 4367f4bb
......@@ -104,8 +104,7 @@ class ModelTpServer:
else server_args.max_running_requests
)
self.max_running_requests = min(
self.max_running_requests,
self.model_runner.req_to_token_pool.size - 1
self.max_running_requests, self.model_runner.req_to_token_pool.size - 1
)
self.int_token_logit_bias = torch.tensor(
get_int_token_logit_bias(self.tokenizer, self.model_config.vocab_size)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment