Back to Freedom.Tech
Project AI

vLLM

High-throughput, memory-efficient LLM inference and serving engine.

90k Stars
21k Forks
14
Releases tracked
GitHub releases
Source type
8 days
Avg cadence
May 2026
First tracked
1d ago
Latest

Release history

AI release Aug 26, 2026

vLLM 0.28.0

584 commits from 270

AI release Aug 11, 2026

vLLM 0.27.1

VLLM adds support for quantized DSpark Markov heads, enabling efficient inference with compressed attention mechanisms

AI release Aug 10, 2026

vLLM 0.27.0

561 commits from 242; Review the changelog before upgrading production inference workloads

AI release Jul 27, 2026

vLLM 0.26.0

VLLM 0.26.0 adds Inkling model support, DeepSeek-V4 performance optimizations, fp32 generation heads, flexible attention backends, and mature KV offloading with tiered storage

AI release Jul 25, 2026

vLLM 0.26.0

411 commits from 212; Check release notes for model and hardware support changes

AI release Jul 14, 2026

vLLM 0.25.1

VLLM 0.25.1 fixes FFmpeg import blocking model startup and mixed-dtype allreduce corruption in quantized models

AI release Jul 11, 2026

vLLM 0.25.0

558 commits, 232; Compatibility and performance sweep

AI release Jun 29, 2026

vLLM 0.24.0

571 commits from 256; No breaking changes called out in summary

AI release Jun 15, 2026

vLLM 0.23.0

DeepSeek-V4 hardening, Model Runner V2 expansion to Llama/Mistral, Rust frontend maturation with streaming and LoRA endpoints, Gemma 4 support, Transformers v5 compatibility, multi-tier KV cache offloading

AI release Jun 12, 2026

vLLM 0.23.0

Minimax M3 models remain unsupported in this version

AI release Jun 5, 2026

vLLM 0.22.1

VLLM 0.22.1 adds Mellum v2 support, enables zentorch-accelerated quantized inference on AMD Zen CPUs, and fixes multi-node Ray serving hangs and model initialization regressions

AI release May 29, 2026

vLLM 0.22.0

VLLM 0.22.0 hardens DeepSeek V4 with fused kernels and CUDA graphs, advances Model Runner V2 toward default, adds experimental Rust frontend, and enables multi-tier KV cache offloading for extended memory management

AI release May 15, 2026

vLLM 0.21.0

VLLM 0.21.0 adds KV offload + hybrid memory allocator integration, speculative decoding with thinking budgets, TOKENSPEED_MLA for Blackwell, and requires C++20 and Transformers v5

AI release May 10, 2026

vLLM 0.20.2

VLLM 0.20.2 fixes DeepSeek V4 sparse attention hangs, KV cache allocation failures, gpt-oss torch.compile compatibility, and Qwen3-VL load issues