rehman 09bdfd6628 fix: truncate conversation tokens to model context window in chat_cli ... Fixes #581. When conversation_tokens grows beyond model.config.sequence_len, engine.generate() received a zero-dimension tensor and crashed with a matmul shape error. Add a sliding window guard before each generate() call that keeps the most recent (sequence_len - max_new_tokens) tokens, re-inserts bos to preserve a well-formed sequence, and notifies the user when truncation occurs.		2026-05-06 01:29:20 +05:00
..
test_attention_fallback.py	delete autocast, an unnecessary thorn in my side, manage dtypes directly	2026-03-04 23:55:30 +00:00
test_context_truncation.py	fix: truncate conversation tokens to model context window in chat_cli	2026-05-06 01:29:20 +05:00
test_engine.py	Fix MockModel's device definition (#535)	2026-02-17 16:03:46 -08:00