# vLLM v0.7.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.7.0
- **Released:** Jan 27, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.7.0/

## Executive Summary (TL;DR)
vLLM v0.7.0. Source highlight: vLLM's V1 engine is ready for testing! This is a rewritten engine designed for performance and architectural simplicity. You can turn it on by setting environment variable `VLLM_USE_V1=1`. See our blog for more details. (44 commits).

## New Features
- New generative models: CogAgent (#11742), Deepseek-VL2 (#11578, #12068, #12169), fairseq2 Llama (#11442), InternLM3 (#12037), Whisper (#11280)
- New pooling models: Qwen2 PRM (#12202), InternLM2 reward models (#11571)
- VLM: Merged multi-modal processor is now ready for model developers! (#11620, #11900, #11682, #11717, #11669, #11396)
- Any model that implements merged multi-modal processor and the `get_*_embeddings` methods according to this guide is automatically supported by V1 engine.
- Apple: Native support for macOS Apple Silicon (#11696)
- AMD: MI300 FP8 format for block_quant (#12134), Tuned MoE configurations for multiple models (#12408, #12049), block size heuristic for avg 2.8x speedup for int8 models (#11698)

## Improvements
- vLLM's V1 engine is ready for testing! This is a rewritten engine designed for performance and architectural simplicity. You can turn it on by setting environment variable `VLLM_USE_V1=1`. See our blog for more details. (44 commits).
- 28 CI and build enhancements, including testing for nightly torch (#12270) and inclusion of genai-perf for benchmark (#10704).
- 58 documentation enhancements, including reorganized documentation structure (#11645, #11755, #11766, #11843, #11896).
- [Misc] Improve BNB loader to handle mixture of sharded and merged weights with same suffix
- [V1] Improve TP>1 Error Handling + Stack Trace
- [Frontend] Improve `StreamingResponse` Exception Handling

## Bug Fixes
- more than 161 bug fixes and miscellaneous enhancements
- [V1] Fix yapf
- [CI] Fix broken CI
- [misc] fix typing
- [BugFix] Deepseekv3 broke quantization for all other methods
- [Bugfix] Fix TeleChat2ForCausalLM weights mapper

## Upgrade Command
```bash
python -m pip install 'vllm==0.7.0'
```