From a707eaebc6c2ae61cd879130d7517d121859d20c Mon Sep 17 00:00:00 2001 From: justheuristic Date: Mon, 29 Aug 2022 20:43:37 +0300 Subject: [PATCH] review --- src/server/handler.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/server/handler.py b/src/server/handler.py index e23b042..27ed562 100644 --- a/src/server/handler.py +++ b/src/server/handler.py @@ -50,7 +50,7 @@ class TransformerConnectionHandler(ConnectionHandler): if not requested_uids: raise ValueError("User must specify at least one block for inference, but got none") - assert isinstance(max_length, int), f"rpc_inference metadata must contain int seq_length, got {max_length}" + assert isinstance(max_length, int), f"rpc_inference metadata must contain int max_length, got {max_length}" if not 0 <= max_length <= self.inference_max_length: raise ValueError(f"Cannot allocate KV cache for {max_length} tokens, max = {self.inference_max_length}")