TensorRT-LLMs/tests/unittest/_torch/executor
QI JUN 89e0117097
[TRTLLM-8836][chore] Create ModelEngine from LlmArgs (#8600)
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com>
2025-11-01 05:26:06 -07:00
..
test_chunked_logits.py [TRTLLM-8031][feat] Add chunked return_generation_logits logic (#7831) 2025-10-01 12:47:07 -04:00
test_executor_request_queue.py [TRTLLM-7733][feat] Executor changes to support helix parallelism (#7972) 2025-10-01 22:13:03 -04:00
test_overlap_scheduler_input.json [None][ci] move unittests to sub-directories (#6635) 2025-08-20 05:42:22 -04:00
test_overlap_scheduler.py [TRTLLM-7349][feat] Adding new orchestrator type -- ray (#7520) 2025-10-04 08:12:24 +08:00
test_pytorch_model_engine.py [TRTLLM-8836][chore] Create ModelEngine from LlmArgs (#8600) 2025-11-01 05:26:06 -07:00
test_resource_manager.py [TRTLLM-8483][chore] Refine scheduler_config and peft_cache_config in create_py_executor (#8451) 2025-10-22 08:33:48 +08:00
test_router_dealer_ipc.py [https://nvbugs/5503440][fix] Fix potential hang due to wrong type of ZMQ socket and protocol for worker_init_status_queue (#7646) 2025-09-19 18:13:33 +08:00