w_lihongyan f03f3b0899 fix: raise when the engine rejects a request in LLM.generate ... add_request() returns None when it drops a request with invalid token ids, but LLM._add_request() ignored the return value, so generate() could return fewer results than the input prompts — silently misaligning results[i] with prompts[i]. Fail loudly with a clear error instead. Co-Authored-By: Kscc <noreply@owtffssent.com>		2026-10-27 11:30:43 +08:00
..
test_llm_add_request.py	fix: raise when the engine rejects a request in LLM.generate	2026-10-27 11:30:43 +08:00