APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
newsInfraGpus

vLLM v0.28.0 Ships Sparse Attention and 60% Faster Speculative Decoding

The latest vLLM release lands 584 commits from 270 contributors, with big performance wins for Kimi-K3, DeepSeek-V4, and speculative decoding.

vLLM v0.28.0 Ships Sparse Attention and 60% Faster Speculative Decoding
Source
vLLM
Published
Author
AlphaSignal Newsroom
Read
1 min read

The latest vLLM release lands 584 commits from 270 contributors, with big performance wins for Kimi-K3, DeepSeek-V4, and speculative decoding.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Project Maya Runs 321B GLM-5.3-Flash on a Single Workstation GPU
AlphaSignal · repo

Project Maya Runs 321B GLM-5.3-Flash on a Single Workstation GPU

vLLM Runs MiniMax M3 at 7.84x Faster on NVIDIA's Vera Rubin
vLLM · news

vLLM Runs MiniMax M3 at 7.84x Faster on NVIDIA's Vera Rubin

MiaAI's Qwen3.8-27B Installer Boosts JSON and Code Speed by 78%
AlphaSignal · repo

MiaAI's Qwen3.8-27B Installer Boosts JSON and Code Speed by 78%