TensorRT-LLMs/tensorrt_llm/_torch/speculative
kris1025 a7ea544dbe
[TRTLLM-7384][feat] enable rejection sampling for CDL (#7731)
Signed-off-by: linquanh <linquanh@nvidia.com>
2025-10-12 20:38:48 +08:00
..
__init__.py [None][feat] Draft: Save state first pass (#7012) 2025-10-01 18:40:55 -04:00
auto_heuristic.py [None][feat] Clean up ngram auto mode, add max_concurrency to configs (#6676) 2025-08-07 12:51:47 -04:00
drafter.py [None][feat] Draft: Save state first pass (#7012) 2025-10-01 18:40:55 -04:00
drafting_loops.py [TRTLLM-7384][feat] enable rejection sampling for CDL (#7731) 2025-10-12 20:38:48 +08:00
eagle3.py [None][fix] Fix MTP 2-model (#8115) 2025-10-03 10:13:50 -07:00
interface.py [None][fix] Fix MTP illegal memory access (#8161) 2025-10-07 14:02:55 -04:00
model_drafter.py [TRTLLM-7384][feat] enable rejection sampling for CDL (#7731) 2025-10-12 20:38:48 +08:00
mtp.py [TRTLLM-6393][feat] add static tree sampling and verification (#7161) 2025-09-26 13:16:16 -04:00
ngram.py [TRTLLM-6668][feat] Enable overlap scheduler for two-model spec decoding (#7651) 2025-09-16 07:33:44 +08:00
save_hidden_state.py [None][feat] Draft: Save state first pass (#7012) 2025-10-01 18:40:55 -04:00
spec_tree_manager.py [TRTLLM-6393][feat] add static tree sampling and verification (#7161) 2025-09-26 13:16:16 -04:00
utils.py [None][fix] Fix MTP 2-model (#8115) 2025-10-03 10:13:50 -07:00