chore(deps): bump vllm from 0.20.0 to 0.20.2

[dependabot]

Bumps vllm from 0.20.0 to 0.20.2.

Release notes

Sourced from vllm's releases.

v0.20.2

vLLM v0.20.2

Highlights

This release features 6 commits from 6 contributors (0 new)!

This is a small patch release with bug fixes for DeepSeek V4, gpt-oss, and Qwen3-VL

Bug Fixes

• DeepSeek V4 sparse attention: Re-enable the persistent topk path on Hopper and ensure the memset kernel runs at CUDA graph capture time regardless of max_seq_len, fixing the MTP=1 hang on DeepSeek V4 (#41665, revert of #41605).
• DeepSeek V4 KV cache: Fixed a "failure to allocate KV blocks" error in the V1 engine KV cache manager (#41282).
• gpt-oss MXFP4 + torch.compile: Plumbed hidden_dim_unpadded through the moe_forward fake op so MXFP4 works under torch.compile on v0.20.x (#42002, backport of #41646).
• Qwen3-VL: Removed an invalid deepstack boundary check that could fail under heavy load (#40932).

Contributors

@​ywang96, @​zyongye, @​stecasta, @​wzhao18, @​Isotr0py, @​khluu

v0.20.1

vLLM v0.20.1

This is a patch release on top of v0.20.0 primarily focused on DeepSeek V4 stabilization and performance improvements, along with several important bug fixes.

DeepSeek V4

• Base model support (#41006).
• Multi-stream pre-attention GEMM (#41061), configurable pre-attn GEMM knob (#41443), and tuned default VLLM_MULTI_STREAM_GEMM_TOKEN_THRESHOLD (#41526).
• BF16 and MXFP8 all-to-all support for FlashInfer one-sided communication (#40960).
• PTX cvt instruction for faster FP32->FP4 conversion (#41015).
• Integrated tile kernels (head_compute_mix_kernel) for optimized head computation (#41255).
• Guard megamoe flag with Pure TP (#41522).
• Fixed persistent topk cooperative deadlock at TopK=1024 (#41189) and inter-CTA init race on RadixRowState (#41444), with temporary disable of persistent topk as a workaround (#41442).
• Fixed import error due to AOT compile cache loading (#41090).
• Fixed torch inductor error (#41135).
• Fixed repeated RoPE cache initialization (#41148).
• Fixed missing type conversion for non-streaming tool calls in DSV3.2/V4 (#41198).

Bug Fixes

• Fixed max_num_batched_token not being captured in CUDA graph (#40734).
• Fixed num_gpu_blocks_override not accounted for in max_model_len checks (#41069).
• Auto-disable expandable_segments around cumem memory pool (#40812).
• Fixed BailingMoE linear layer (#40859) and MLA RoPE rotation for BailingMoE V2.5 (#41185).
• Fixed reasoning parser kwargs not being passed to structured output (#41199).
• [ROCm] Fixed input_ids and expert_map args for Quark W4A8 GPT-OSS (#41165).

List of contributors

@​BugenZhao, @​chaunceyjiang, @​gau-nernst, @​ghphotoframe, @​Isotr0py, @​jeejeelee, @​khluu, @​njhill, @​Rohan138, @​wzhao18, @​youkaichao, @​ywang96, @​ZJY0516, @​zixi-qi, @​zyongye

Commits

• bc150f5 [CI] Automate Docker Hub release image publishing (#40415)
• 9bc5a0d [Bugfix] Remove invalid deepstack boundary check for Qwen3-VL (#40932)
• fa8acca [Bugfix] Fix failure to allocate KV blocks error (#41282)
• 637495c [Bugfix] Plumb hidden_dim_unpadded through moe_forward fake to fix gpt-oss MX...
• fbd51e3 [Bugfix] Fix condition to clear persistent topk so that it can be captured re...
• 75b3867 Revert "Temporary disable persistent topk for Hopper (#41605)"
• 132765e Revert "[DSv4] Use cvt PTX for FP32->FP4 conversion (#41015)"
• 43a21e6 Temporary disable persistent topk for Hopper (#41605)
• f98b274 [DSv4] Tune default value of VLLM_MULTI_STREAM_GEMM_TOKEN_THRESHOLD (#41526)
• 228d225 [DSV4] Guard megamoe flag with Pure TP (#41522)
• Additional commits viewable in compare view

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!