# vLLM v0.20.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.20.0
- **Released:** Apr 27, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.20.0/

## Executive Summary (TL;DR)
vLLM v0.20.0. Source highlight: This release features 752 commits from 320 contributors (123 new)!

## Breaking Changes & Deprecations
- PyTorch 2.11 upgrade** (#34644): vLLM ships on torch 2.11 for CUDA, and XPU is now also on torch 2.11 (#37947) — XPU is no longer pinned to 2.10. This is a breaking change for environment dependency.
- Pooling ecosystem**: Pooling entrypoints overhauled across scoring (#28631), pooling (#39153), and cleanup (#39675); preprocessing/postprocessing offloaded to thread pool (#39763); async scheduling disabled by default for pooling (#39592); `logit_scale` added to PoolerConfig (#39435), then renamed `logit_bias`/`logit_scale` → `logit_mean`/`logit_sigma` for affine score calibration (#39530) — breaking. `LLM.reward` deprecated; use `LLM.encode` instead (#40688).
- Breaking Changes 1. **PyTorch 2.11 + CUDA 13.0(.2) default** — environment dependency change, now applied to XPU as well. 2. **Transformers v5** is the supported baseline (#30566).

## New Features
- **Python 3.14**: Added to the supported Python version list (#34770).
- **vLLM IR**: Initial IR skeleton with rms_norm op (#33825), OOT-platform kernel imports (#38807), gemma_rms_norm reworked on IR (#39014), and IR op testing/benchmarking infra added (#40167) — foundation for future kernel work.
- **Executor**: RayExecutorV2 introduced (#36836); unified engine process monitoring with Ray backend (#35862).
- **NVIDIA**: swapAB support for SM120 CUTLASS blockwise FP8 GEMM (#38325), MXFP4 W4A4 CUTLASS MoE for SM100 (#37463), TRTLLM GEN NVFP4 MoE with non-512-aligned hidden dims via weight padding (#39510), TRTLLM FP8 MoE with shuffled weights + BlockMajorK layout (#38993), fused qknorm+rope kernel on SM9.0 (#37376), tuned fused_moe config for RTX PRO 6000 Blackwell (#39183), ViT full CUDA graph for Qwen3-VL video (#38061), `--enable-vit-cuda-graph` for VLM examples (#40580), default `max_frames_per_ba
- **Pooling ecosystem**: Pooling entrypoints overhauled across scoring (#28631), pooling (#39153), and cleanup (#39675); preprocessing/postprocessing offloaded to thread pool (#39763); async scheduling disabled by default for pooling (#39592); `logit_scale` added to PoolerConfig (#39435), then renamed `logit_bias`/`logit_scale` → `logit_mean`/`logit_sigma` for affine score calibration (#39530) — breaking. `LLM.reward` deprecated; use `LLM.encode` instead (#40688).
- **CUDA 13.0** default with updated architecture lists and cleaned build-args (#39878); CUDA bumped to 13.0.2 to match PyTorch 2.11.0 (#40669); sm_110 (Jetson Thor) added (#39233).

## Improvements
- **Performance**: Optimize batch invariant with fused rms norm — 2.1% E2E latency improvement (#40413); avoid `seq_lens_cpu` GPU→CPU sync (#40654); cache `InductorPass.hash_source` (#39328); skip FX-graph deserialization on loading for faster warm compile (#40151); CUDAGraph memory profiling enabled by default for clearer startup memory accounting (#38284).
- **TPU**: tpu-inference upgraded to 0.18.0 (#40395).
- **GDN / Mamba**: Kernel fusion in GDN (#37813), TMA aligned with upstream FLA (#38981), GPU↔CPU syncs eliminated in prefill and spec-decode paths (#38361, #38047).
- **Other**: DeepGEMM integrated into the vLLM wheel via CMake (#37980), Lustre FS checkpoint prefetching enabled by default (#39422), Gemma4 fused routing Triton kernel (#39083), Gemma4 embed_input_ids GPU/CPU sync removed (#39234), Nemotron VL image/video preprocessing optimized (#40283), SiLU block-quant fusion v1 (#32996), bilinear_pos_embed Triton kernel for ViT (#37948), mean-pooling optimization (~5.9% throughput) (#38559), redundant-sync removal for pooling (~3.7% throughput) (#39113), H2D
- **LLM / CLI**: Structured-output special tokens preserved in offline `LLM.chat` (#39352), `use_audio_in_video` passable at `vllm serve` for nemotron-nano-vl (#38538), deferred imports save ~2s CLI startup (#40056), improved MM-input-too-long error message (#39409), warning when FP8 KV cache misses prefill query quant (#39752), clearer DCP error message (#28443), `--model` deprecation warning updated (#39518), Mimo reasoning/tooling parsers mapped (#40089), human-readable `k/K/m/M…` suffix in JSO

## Bug Fixes
- **DeepSeek V4**: Initial DeepSeek V4 support landed (#40860), with DSML token-leakage fix in DSV4/3.2 (#40806), DSA + MTP IMA fix (#40772), and a silu clamp limit on the shared expert (#40950).
- **Transformers v5**: vLLM now runs on HuggingFace `transformers>=5` (#30566), with vision-encoder torch.compile bypass (#30518) and continued v4/v5 compat fixes including PaddleOCR-VL image processor `max_pixels` (#38629), Mistral YaRN warning (#37292), and Jina ColBERT rotary inv_freq recompute (#39176).
- **Model Runner V2 advances**: Eagle prefill full-CUDA-graph (#37588), auto-resolve cudagraph mode/sizes from attention backend (#32936), fused probabilistic rejection sample kernels (#38496), config validation for unsupported features (#38758), piecewise-fallback disabled for eagle draft decodes (#39773), multiple prompt-logprobs support (#39937), prefill warmup coverage (#40746), and a fix for accuracy regression caused by stale sampled/draft tokens (#39833).
- Gemma4 series: fast prefill (#38879), quantized MoE (#39045), Eagle3 (#39450), block-local attention + YaRN for Gemma3 (#39823), bidirectional vision attention for sliding layers (#40534), token-repetition fix via dynamic BOS (#39842), multimodal embedder norm-order fix (#40411), plus a string of streaming/tool-call fixes (#38844, #38909, #38992, #39114, #39679, #39027).
- Other: Nano-Nemotron-VL static image inputs fix (#40724); Qwen3 MoE no longer calls gate twice (#40664); DeepSeek V2-Lite accuracy drop fix (#40673); Parakeet UX / perf enhancements (#39423); ColModernVBERT updated for latest HF checkpoint (#39307); NemotronH default `mamba_ssm_cache_dtype=float32` with NemotronHNanoVLV2 auto-hook (#39032); new TP plan styles for the Transformers backend (#40467); GLM-5.1 fix on ROCm (#40763).
- **Model Runner V2**: Full CUDA graph for eagle prefill (#37588), auto cudagraph mode/sizes based on attention backend (#32936), fused probabilistic rejection-sample kernels (#38496), config validation (#38758), eagle-draft piecewise fallback disabled (#39773), multiple prompt logprobs (#39937), prefill warmup coverage (#40746), stale sampled/draft tokens accuracy fix (#39833).

## Upgrade Command
```bash
python -m pip install 'vllm==0.20.0'
```