TensorRT-LLMs/tensorrt_llm/_torch/speculative
Izzy Putterman 8097be7e9c
[None][feat] Eagle, use last hidden post norm (#7546)
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
2025-09-15 12:23:57 -04:00
..
__init__.py [None][feat] Clean up ngram auto mode, add max_concurrency to configs (#6676) 2025-08-07 12:51:47 -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] Make the should_use_spec_decode logic a bit smarter (#7112) 2025-09-10 12:53:59 +08:00
drafting_loops.py [https://nvbugs/5502352][fix] Fix 2-model CDL path (#7543) 2025-09-06 23:53:27 -04:00
eagle3.py [None][feat] Eagle, use last hidden post norm (#7546) 2025-09-15 12:23:57 -04:00
interface.py [TRTLLM-7408][feat] Wrap MOE with custom op. (#7277) 2025-09-09 12:18:56 -04:00
model_drafter.py [TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) (#6948) 2025-09-03 15:16:11 -07:00
mtp.py [TRTLLM-7408][feat] Wrap MOE with custom op. (#7277) 2025-09-09 12:18:56 -04:00
ngram.py [None][refactor] Move draft token padding out of Drafter (#7134) 2025-08-27 11:07:50 +02:00
utils.py [None][feat] MultiLayer Eagle (#7234) 2025-09-04 10:49:13 -04:00