biondizzle
a86d6d90a5
- Copied deepseek_v4_encoding.py from vLLM tree to encoding/ - Replaced hand-rolled prompt construction with encode_messages() - --chat-mode → --thinking-mode (thinking|chat) - The official encoder handles: BOS, User/Assistant tokens, thinking mode, tool calls, and all special token placement. It can't drift. - This is the same code path inference engines will use.
2 lines
19 B
Python
2 lines
19 B
Python
# encoding package
|