# vLLM 0.17: PyTorch 2.10 Upgrade and FlashAttention 4 Integration

- Link: https://thestackobserver.com/vllm-0-17-pytorch-2-10-upgrade-and-flashattention-4-integration/
- Published: 2026-03-16T08:10:14-04:00
- Author: Stackxx

[vLLM](https://github.com/vllm-project/vllm) has released version 0.17, featuring
699 commits from 272 contributors including 48 new contributors. This release brings
major infrastructure upgrades and performance improvements for LLM inference.

## PyTorch 2.10 Upgrade

vLLM 0.17 upgrades to **PyTorch 2.10.0**, a breaking change for environment dependencies.
Users should update their environments accordingly.

**Note for CUDA 12.9+ users**: If you encounter `CUBLAS_STATUS_INVALID_VALUE` errors,
this is caused by a CUDA library mismatch. Solutions include removing system CUDA
paths from `LD_LIBRARY_PATH` or reinstalling with specific CUDA version flags.

## FlashAttention 4 Integration

vLLM now supports the **FlashAttention 4** backend, bringing next-generation attention
performance. FlashAttention 4 delivers improved memory efficiency and faster attention
computation, particularly beneficial for long-context workloads.

## Model Runner V2 Improvements

Model Runner V2 has reached a major milestone with **Pipeline Parallel** support,
enabling more efficient distributed inference across multiple GPUs.

## New Model Support

vLLM 0.17.1 adds support for **Nemotron 3 Super**, NVIDIA’s 122B parameter model
with strong reasoning capabilities. This model is also available through Ollama 
for local deployment.

## Bug Fixes and Improvements

 * Fixed activation_type passing for TensorRT-LLM fused MoE
 * Re-enabled expert parallelism for TensorRT-LLM MoE FP8 backend
 * Fixed DeepSeek-V3.2 MTP indexer handling
 * Zero freed SSM cache blocks on GPU for Mamba and Qwen3.5

## Sources

 * [vLLM v0.17.0 Release](https://github.com/vllm-project/vllm/releases/tag/v0.17.0)
 * [vLLM v0.17.1 Release](https://github.com/vllm-project/vllm/releases/tag/v0.17.1)
 * [vLLM Documentation](https://docs.vllm.ai)