← The Wire

Infra2026-06-23 · source-backed

vLLM ships multi-tier KV-cache offloading and batch-invariant FP8 for a 28.9% latency cut.

Confidence
source-backed
Sources
1
Redaction
passed

Story

June 2026 releases add a multi-tier KV-cache offloading framework (Python filesystem tier plus Mooncake disk offload, extending past CPU memory), make Model Runner V2 the default for Qwen3 dense models, and land Cutlass FP8 for batch-invariant inference. (vLLM) If you self-host inference, the KV offloading tiers let you serve longer contexts and higher concurrency on the same GPUs. The batch-invariant FP8 also gives reproducible outputs across batch sizes, which quietly fixes a real headache for evals and caching where the same input shouldn't drift by batch.

Related stories

Each link below shares sources, entities, or timing with this story.

  1. Shared entities / Same source domain / Shared topic / Earlier coverage / Downstream implication

    llama.cpp Gets Backend-Agnostic Tensor Parallelism, and the NVIDIA Tax Just Got Optional

    Both cover CPU, GPUs, Qwen3; reported by the same outlet (github.com); overlapping topics (context, inference, model).

  2. Shared entity: FP8 / Same source / Shared topic / Earlier coverage

    vLLM v0.20.2 Ships Model Runner V2: 56% Throughput Improvement on GB200.

    Both cover FP8; cite the same source (vLLM); overlapping topics (inference, model).

  3. Shared entity: Qwen3 / Same source domain / Shared topic / Earlier coverage

    Gemma 4 Ships Under Apache 2.0 and the Numbers Are Absurd

    Both cover Qwen3; reported by the same outlet (github.com); overlapping topics (dense, inference, model).

  4. llama.cpp just made low-bit KV cache dramatically more accurate, nearly for free.

    Both cover Qwen3; reported by the same outlet (github.com); overlapping topics (caching, context).

  5. Shared entity: CPU / Same source domain / Shared topic / Earlier coverage

    Microsoft Foundry-Local: One SDK to Replace Ollama, llama.cpp, and Whisper.cpp. No Cloud Required.

    Both cover CPU; reported by the same outlet (github.com); overlapping topics (context, model).

  6. Shared entity: Qwen3 / Same source domain / Shared topic / Earlier coverage

    Nvidia's Blackwell Ultra Just Made Self-Hosted Inference a Real Option: 2.49M Tokens/Sec, 30 Cents Per Million

    Both cover Qwen3; reported by the same outlet (github.com); overlapping topics (inference, model).

  7. Shared entity: Python / Same source domain / Shared topic / Earlier coverage

    Timber — Ollama for Classical ML (476 stars, 188 HN points)

    Both cover Python; reported by the same outlet (github.com); overlapping topics (inference, model).

  8. Shared entity: Qwen3 / Same source domain / Shared topic / Earlier coverage

    Alibaba Launches Qwen 3.5 — The First Agentic-Native Foundation Model

    Both cover Qwen3; reported by the same outlet (github.com); overlapping topics (context, model).

Source trail

Entities

Provenance

AI generated
no
Story unit
2026-06-23-vllm-ships-multi-tier-kv-cache-offloading-and-batch-invariant-fp8-for-a-28-9-latency-cut
Labels
source-backed, canonical briefing excerpt