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
..
distributed	initial commit	2026-10-20 12:09:42 +08:00
engine	initial commit	2026-10-20 12:09:42 +08:00
entrypoints	fix: raise when the engine rejects a request in LLM.generate	2026-10-27 11:30:43 +08:00
models	initial commit	2026-10-20 12:09:42 +08:00
ve	initial commit	2026-10-20 12:09:42 +08:00
worker	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
conftest.py	initial commit	2026-10-20 12:09:42 +08:00
test_cuda_sync_guards.py	initial commit	2026-10-20 12:09:42 +08:00