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

[None][doc] Add acknowledgements in scaffolding tech blog (#7983)

Browse Source 
Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>
This commit is contained in:
WeiHaocheng 2025-09-25 23:07:13 +08:00 committed by GitHub
parent 57ff5f4c0d
commit 4b0570a0d6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.md
View File

@ -16,6 +16,7 @@ By NVIDIA TensorRT LLM Team and UCSD Hao AI Lab
- [Introduction for Dynasor](#dynasor-introduction)
- [Implement Dynasor-CoT in Scaffolding](#dynasor-cot-implement-in-scaffolding)
- [Implement Dynasor-CoT based Majority Voting in Scaffolding](#dynasor-cot-based-majority-vote-in-scaffolding)
- [Acknowledgements](#dynasor-acknowledgements)
- [Reference](#dynasor-reference)
- [Feature List on Scaffolding](#scaffolding-feature-list)
- [Future Work](#scaffolding-future-work)
@ -401,6 +402,11 @@ llm = ScaffoldingLlm(
results = llm.generate(prompts)
```
### Acknowledgements
This work demonstrates an outstanding example of cross-team collaboration between the TensorRT LLM and UCSD Hao AI Lab. We sincerely appreciate the support from everyone who contributed to making this happen.
### Reference
[1] Y. Fu*, J. Chen*, Y. Zhuang, Z. Fu, I. Stoica, and H. Zhang, "Dynasor: More Efficient Chain-of-Thought Through Certainty Probing," Hao-AI-Lab Blog, Feb. 16, 2025. [Online]. Available: https://hao-ai-lab.github.io/blogs/dynasor-cot/