vLLM v0.28.0rc2 introduces DFlash2 feature for speculative decoding
The vLLM project adds DFlash2, a speculative decoding technique combining local convolution and candidate selection, in release candidate v0.28.0rc2.
1 source · cross-referenced
- vLLM release v0.28.0rc2 adds DFlash2 for speculative decoding with local convolution and candidate selection
- The feature is introduced via pull request #52816 and tagged by a maintainer on August 21
- vLLM is an open-source library for large language model inference
The vLLM project published release candidate v0.28.0rc2, which introduces DFlash2, a speculative decoding feature that combines local convolution with a candidate selector.
DFlash2 is delivered via pull request #52816 and was tagged by maintainer SubSir on August 21.
vLLM is an open-source library designed to optimize inference for large language models, commonly used to serve models in production environments.
Speculative decoding aims to reduce the number of tokens generated by proposing multiple candidate tokens and verifying them in parallel, which can improve throughput.
- Oct 14, 2026 · TechCrunch — AI
Science Corporation implants vision-restoring PRIMA chip in first Stargardt disease patient
Trust78 - Oct 13, 2026 · TechCrunch — AI
Flox Intelligence raises $5M and launches edge AI devices to deter wildlife from critical infrastructure
Trust79 - Oct 13, 2026 · Hugging Face
Hugging Face releases LFM2.5-24B-A2B, a 24B-parameter reasoning agent with 2B active parameters for on-device use
Trust79