vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

Affected: PyPI: vllm

### Summary

The `extract_hidden_states` speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a `RuntimeError` that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (`repetition_penalty`, `frequency_penalty`, or `presence_penalty`).

A single request with a penalty parameter (e.g., `"repetition_penalty": 1.1`) is sufficient to crash the server. The crash is deterministic and immediate — no concurrency, race condition, or special workload is required.

### Details

In vLLM v0.17.0, the `extract_hidden_states` proposer's `propose()` method returned `sampled_token_ids.unsqueeze(-1)`, producing a tensor of shape `(batch_size, 1)`.

In [PR #37013](https://github.com/vllm-project/vllm/pull/37013) (first released in v0.18.0), the KV connector interface was refactored out of `propose()`. The return type changed from `tuple[Tensor, KVConnectorOutput | None]` to `Tensor`, and the `.unsqueeze(-1)` call was removed along with the KV connector output:

```python # Before (v0.17.0): return sampled_token_ids.unsqueeze(-1), kv_connector_output # shape (batch_size, 1)

# After (v0.18.0+): return sampled_token_ids # shape (batch_size, 2) after first decode step ```

The refactor missed that `sampled_token_ids` changed semantics between the first and subsequent decode steps. After the first decode step, the rejection sampler allocates its output as `(batch_size,…

Affected: PyPI: vllm

vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

vllm: vLLM: Server-Side Request Forgery allows access to internal services via controlled batch input vLLM: vLLM: Denial of Service due to excessive video frame processing vllm: vLLM: Denial of Service via excessively large 'n' parameter in OpenAI-compatible API vllm: vLLM: Arbitrary code execution via malicious HuggingFace model vllm: vLLM: Denial of Service via malformed tensor shape in speculative decoding

Ein entfernter, authentisierter Angreifer kann eine Schwachstelle in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.