kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
5aa958a11a
TensorRT-LLMs/tensorrt_llm/_torch/speculative
History
Raayan Dhar e3268a4221
[TRTLLM-5847][feat] Support n-gram speculative decoding with disagg (#5732) 
Signed-off-by: raayandhar <rdhar@nvidia.com>
2025-07-08 09:39:58 -04:00
..
__init__.py [TRTLLM-6291] feat: Add user-provided speculative decoding support (#5204) 2025-07-07 16:30:43 +02:00
draft_target.py Speculation: Draft Target in new FW (#4558) 2025-06-17 02:26:08 +08:00
drafter.py [TRTLLM-6291] feat: Add user-provided speculative decoding support (#5204) 2025-07-07 16:30:43 +02:00
eagle3.py MTP and derivatives: Align sample state with trtllm sampler sample state (#5675) 2025-07-03 19:55:48 +02:00
interface.py [TRTLLM-6291] feat: Add user-provided speculative decoding support (#5204) 2025-07-07 16:30:43 +02:00
mtp.py MTP and derivatives: Align sample state with trtllm sampler sample state (#5675) 2025-07-03 19:55:48 +02:00
ngram.py [TRTLLM-5847][feat] Support n-gram speculative decoding with disagg (#5732) 2025-07-08 09:39:58 -04:00
user_provided.py [TRTLLM-6291] feat: Add user-provided speculative decoding support (#5204) 2025-07-07 16:30:43 +02:00
utils.py [TRTLLM-6291] feat: Add user-provided speculative decoding support (#5204) 2025-07-07 16:30:43 +02:00