refactor : merge max_prompt_len into max_seq_len, replace assert with raise

- Engine/Scheduler/TaskManager: merge max_prompt_len into max_seq_len
- train.py: replace bare assert with ValueError/FileNotFoundError
- server.py: add --max_seq_len CLI option
- engine.py: remove dead page_size param

astrai/inference/engine.py

@@ -111,8 +111,6 @@ class InferenceEngine:
         tokenizer: AutoTokenizer,
         max_batch_size: int = 1,
         max_seq_len: Optional[int] = None,
-        max_prompt_len: int = 2048,
-        page_size: int = 128,
         cache: Optional[KVCache] = None,
     ):
         self.model = model
@@ -122,7 +120,6 @@ class InferenceEngine:
             tokenizer=self.tokenizer,
             max_batch_size=max_batch_size,
             max_seq_len=max_seq_len,
-            max_prompt_len=max_prompt_len,
             cache=cache,
         )