腾讯网

DeepSeeK 突然发布 DSpark，让 AI 的回答不再「挤牙膏」

最近忙着大规模招兵买马的 DeepSeek，也始终没有忘记开源这条主线。今天，DeepSeek 与北京大学团队联合发布论文《DSpark: Confidence-Scheduled Speculative Decoding with ...

DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%

DSpark can make decoding faster, but acceptance quality still determines how much speed the system actually realizes.
Tech Times

NVIDIA Diffusion LLM Hits 2.42x Throughput Without Retraining: Nemotron TwoTower Released

NVIDIA diffusion language model Nemotron TwoTower achieves 2.42x LLM inference throughput without a full retraining run, ...
格隆汇 on MSN

梁文锋署名，DeepSeek发布最新论文

格隆汇6月28日丨在6月中旬获得500亿融资后仅十几天，6月27日，DeepSeek团队联合北京大学发布论文《DSpark: Confidence-Scheduled Speculative Decoding with ...
Developer Tech

NVIDIA: DFlash block diffusion accelerates autoregressive LLMs

Deploying DFlash block diffusion on NVIDIA hardware accelerates autoregressive LLMs during latency-sensitive inference.
Tech Times

DeepSeek Releases DSpark: Speculative Decoding Makes V4 Up to 85 Percent Faster

DeepSeek speculative decoding framework DSpark went live June 27 on V4-Flash and V4-Pro, reporting up to 85 percent faster ...
Analytics India MagazineOpinion

DeepSeek V4 is Now up to 85% Faster With New Inference Technique

The AI giant will use the new capital to fund AI infrastructure, product development, and conduct a major hiring push, with ...