HN
Hacker News
Top
New
Best
Ask
Show
Jobs
dhruvdh
557 karma · joined April 26, 2019
submissions
comments
Accelerating LLM Inference with Parallel Draft Models (PARD)
amd.com
·
1 pts
·
dhruvdh
·
0
Open-sourcing Three EXAONE 3.5 Models: 2.4B, 7.8B, 32B
lgresearch.ai
·
13 pts
·
dhruvdh
·
4
The Tyranny of Possibilities in the Design of Task-Oriented LLM Systems
arxiv.org
·
1 pts
·
dhruvdh
·
3
MoAI Platform – Scale PyTorch, TensorFlow, etc. to Thousands of GPU/NPUs
moreh.io
·
1 pts
·
dhruvdh
·
0
Lamini LLM Finetuning on AMD ROCm: A Technical Recipe
lamini.ai
·
6 pts
·
dhruvdh
·
4
ModuleFormer: Modularity Emerges from Mixture-of-Experts
arxiv.org
·
1 pts
·
dhruvdh
·
1