> ## Content Index
> Fetch the complete content index at: https://ping2prompt.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# vLLM v0.34.0 adds Mistral Large 4, drops Model Runner V1, changes defaults
- URL: https://ping2prompt.com/vllm-v0-34-0-mistral-large-4-model-runner-v1-removed/
- Published: 2026-11-16T23:59:57.000Z
- Updated: 2026-11-18T17:21:29.000Z
- Description: vLLM v0.34.0 adds 10 models led by Mistral Large 4, makes extensible KV cache the default and removes Model Runner V1. Block-size and memory defaults change, so production users should test on staging first.
- Author: Ping2Prompt Newsroom
- Tags: vLLM, AI, #short-ping

## What changed

vLLM v0.34.0 is out, with 1,061 commits from 412 contributors, 120 of them new. It adds 10 models led by Mistral Large 4, makes extensible KV cache the default and removes Model Runner V1.

## What it does

Mistral Large 4 is listed at 1T total and 52B active parameters, in FP8 and NVFP4, and runs on NVIDIA Blackwell/Hopper and AMD MI350\. Extensible KV cache sizes the cache on CUDA and ROCm from the memory actually free after CUDA graph capture and warmup. Model Runner V2 is now the only GPU runner. Nemotron-3.5-Transcribe, a speech model, is served through `/v1/audio/transcriptions`.

## What is verified

All performance numbers below are vLLM's own claims from its release notes. vLLM says extensible KV cache grows the MiniMax-M3 KV cache on H200 from 433k to 672k tokens, at a cost of 6-18% higher TPOT on some H200 models at concurrency 128\. vLLM reports up to 1.95x decode for Step5 NVFP4 MoE on TRTLLM-Gen on 4xGB200\. vLLM lists a known regression: openai/gpt-oss-120b on AMD MI355X is slower than in v0.33.0\. At 8k-input prefill and concurrency 128, throughput is about 24% lower and TTFT about 3x higher. ROCm correctness fixes caused it.

## Running it

The commands and flags in this piece come from the release notes in the sources list, so check them against your own install before running them. Images include `vllm/vllm-openai:v0.34.0` (CUDA 13.0), `vllm/vllm-openai-rocm:v0.34.0`, `vllm/vllm-openai-cpu:v0.34.0` and `vllm/vllm-openai-xpu:v0.34.0`. For CUDA 13.0 wheels, run `pip install vllm`.

ROCm 7.2 artifacts are gone; use the ROCm 10.0 wheels and images. You need `huggingface_hub` \>= 2.0.0, `tokenizers` \>= 0.23.3 and `timm` \>= 1.0.30.

- Default `--block-size` is now 64, up from 16\. Pass `--block-size 16` to keep the old behaviour.
- `gpu_memory_utilization` now defaults to 1.0\. To keep old sizing, pass `--gpu-memory-utilization 0.9` or `--no-enable-extensible-kv-cache`.
- Remove `VLLM_USE_V2_MODEL_RUNNER=0`; it now fails at startup.

## What it means for you

If you run vLLM in production, test this release on a staging box first, because the new memory and block-size defaults change how a server starts and behaves. AMD users running the affected gpt-oss model on that GPU should benchmark their own workload before moving.

## What the sources don't cover

The release notes give no release date, licence, price or hardware minimums for the new models, and no independent benchmarks exist yet.

## Sources

- [github.com/vllm-project/vllm/releases/tag/v0.34.0](https://github.com/vllm-project/vllm/releases/tag/v0.34.0?ref=ping2prompt.com)

Image: [Photo by Steve A Johnson on Unsplash](https://unsplash.com/photos/a-computer-circuit-board-with-a-brain-on-it-%5F0iV9LmPDn0?utm%5Fsource=ping2prompt&utm%5Fmedium=referral)

---

This story was produced with AI assistance from the sources listed above and fact-checked against them before publication. Read our [editorial methodology](https://ping2prompt.com/about-how-we-work/) and the [corrections log](https://ping2prompt.com/corrections/). Spotted an error? Email [editor@ping2prompt.com](mailto:editor@ping2prompt.com).