# vLLM v0.25.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.25.0
- **Released:** Jul 11, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.25.0/

## Executive Summary (TL;DR)
vLLM v0.25.0. Source highlight: vLLM v0.25.0 Release Notes

## New Features
- Video: TorchCodec added as a video decoding backend (#46609).

## Improvements
- GLM-5.2 / DeepSeek: `fused_indexer_q_rope_quant` Triton kernel (1.9–3.3% E2E throughput) (#46862), reduce-scatter MoE all-reduce (3.1–3.2% E2E) (#46635), op fusion for GLM5/DSV3.2 (#46876), `token_to_req_indices` cache for DSv4 (5–6x kernel speedup) (#47474), better DSv4 MXFP8 kernel (#47229), redundant-op removal (#47198, #46651).
- NVIDIA/Blackwell: FlashInfer fused all-reduce tuned for world_size=16 on GB300 (#46392), restored NVFP4 swizzled-scale zero-init to recover Blackwell decode throughput (#45739), CuTeDSL/FA4-MLA warmup infrastructure (#46182), skip cooperative top-K on SM120 (#47164), B12x backend for non-gated MoEs (#43328).
- Kernels: Helion `fused_qk_norm_rope` (#44010) and `silu_and_mul_per_block_quant` (#43994), Triton MLA logits workspace (#46819), swap-AB optimization for fused MoE (#36559), vectorized fp32 `moe_sum` supporting any top-k (#46643), blocking CUDA events to avoid busy-polling the driver lock (#47081).
- AMD/ROCm: moved to torch 2.11 stable ABI (#47128); AITER FlashAttention MLA prefill backend `ROCM_AITER_FA` (#45033); fused shared-expert for GLM-4.5/6/7 (#44313) and MiniMax-M3 (#46474, #46545); AITER MoE optimization for DeepSeek-V4 (#46122); AITER custom all-reduce in CudaCommunicator (#46065); INT3 quantization for quickreduce (#45666).
- RISC-V: RVV path for W4A8 INT4 GEMM (#45269), BF16 on VLEN=256 hardware (#45243), reduced LMUL pressure in INT4 LUT dequant (#47538). POWER: fp16 support on PowerPC (#46135).
- Platform: accelerator-agnostic `get_memory_info` (#44825).

## Bug Fixes
- **The Transformers modeling backend is now as fast as native vLLM** (#47187), and gained FP8 MoE support (#46820), CUDA graph + embed scaling fixes (#48010), and migration of GPTBigCode/Starcoder2 (#30966) and RoBERTa (#47452).
- GLM-5 family: GLM-5 / DeepSeek-V3.2 added to the model zoo (#46808), GLM-5.2 FP32 gate (#47410), GLM MTP post-final-norm fix (#47448), GLM4V startup fix (#47155).
- Transformers backend: now as fast as native vLLM (#47187), FP8 MoE fix (#46820), embed scaling + CUDA graph fix (#48010), GPTBigCode/Starcoder2 (#30966) and RoBERTa (#47452) migration, M-RoPE `mm_token_type_ids` fix (#46552), tied-embedding `lm_head.bias` fix (#46835).
- Voxtral: migrated to mistral-common 1.11.5 audio API (#46705) and realtime token-feedback hang fix (#44461).
- Gemma family: Gemma4 sliding-window/FA4 attention fixes (#47217, #47332), Gemma4 MTP quant_config fix (#47091); DiffusionGemma tensor parallelism (#45719) and HF stability-window semantics (#45965).
- Other fixes: MiniCPM-V 4.6 language-backbone LoRA (#46740) and placeholder grid fix (#45918), pooled Whisper sliding-window sizing (#47071, #47437), Mamba/Mamba2 checkpoint-without-`architectures` crash fix (#46037), DeepSeek-V2 hidden-size and aux-hidden-state fixes (#46986, #46973).

## Upgrade Command
```bash
python -m pip install 'vllm==0.25.0'
```