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
This commit is contained in:
2026-07-27 08:05:11 +08:00
parent 05c7432964
commit 53c804e233
12 changed files with 27 additions and 21 deletions
-1
View File
@@ -109,7 +109,6 @@ def _make_scheduler(model, tokenizer, max_batch_size=8, max_len=128):
tokenizer=tokenizer,
max_batch_size=max_batch_size,
max_seq_len=max_len,
max_prompt_len=max_len,
)