Unverified50% confidenceReleaseExact time
vLLM released release candidate v0.31.0rc3, with the core highlight being the introduction of Randomized Dummy Inputs support for Model Runner V2.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
UnverifiedIn vLLM v0.29.0, Model Runner V2 officially became the default execution engine for all models.70% similarUnverifiedvLLM maintainer Bugen Zhao tagged the vllm-proto component with version proto-v0.4.0, corresponding to commit hash f28a508.67% similarUnverifiedModel Runner V2 gains two capabilities in vLLM v0.28.0: E/P/D separation (Encode/Prefill/Decode disaggregated deployment) and weight offloading.66% similarUnverifiedvLLM v0.28.0rc2 introduces a new speculative decoding feature called DFlash2, which combines two major technical components: local convolution and a candidate selector (PR #52816).66% similarUnverifiedvLLM v0.28.0 introduces DFlash2 and DSpark confidence-scheduled verification in the speculative decoding domain.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/964604API
curl https://kongchang.com/api/v1/knowledge/claims/964604MCP
get_claim(id=964604)