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.
- Aug 23, 2026 · TechCrunch — AI
Harvard’s startup bootcamp integrates AI avatars for instructor-led feedback
Trust74 - Aug 22, 2026 · The Verge — AI
Google adds student-focused study tools to Gemini
Trust79 - Aug 22, 2026 · Simon Willison — everything
llm 0.33 released with embedding key support, template chaining, and reasoning_summary options
Trust84