logotype | Dark Hacker News

1.	Speculative pre-positioning: off-path decode for stateful inference sessions(arxiv.org) 1 points by logotype 47 days ago \| 1 comment
2.	Stateful Inference for Low-Latency Multi-Agent Tool Calling(arxiv.org) 2 points by logotype 84 days ago \| 1 comment
3.	Attention Once Is All You Need: Stateful Transformers(arxiv.org) 3 points by logotype 97 days ago \| 4 comments
4.	1 points by logotype 128 days ago \| discuss
5.	1 points by logotype 141 days ago \| discuss
6.	New inference engine faster than vLLM, SGLang, TRT-LLM(layerscale.ai) 2 points by logotype 181 days ago \| 3 comments