TensorRT-LLMs/examples/scaffolding
Zhenhuan Chen ad15e45f07
[TRTLLM-4638 ][feat] add best of n support with reward model in scaffolding (#3807)
Signed-off-by: Zhenhuan Chen <chenzhh3671@gmail.com>
2025-04-28 17:15:33 +08:00
..
contrib feat(part 2): Enhance the integrated robustness of scaffolding with __init__.py #3305 (#3731) 2025-04-24 18:47:03 +08:00
run_basic_generation.py [TRTLLM-4638 ][feat] add best of n support with reward model in scaffolding (#3807) 2025-04-28 17:15:33 +08:00
run_best_of_n_with_reward.py [TRTLLM-4638 ][feat] add best of n support with reward model in scaffolding (#3807) 2025-04-28 17:15:33 +08:00
run_majority_vote_aime24.py [TRTLLM-4638 ][feat] add best of n support with reward model in scaffolding (#3807) 2025-04-28 17:15:33 +08:00
test.jsonl Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00