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

Affected: vllm-project vllm

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.

GHSA-pr7f-p5mw-fc87 — vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Affected: PyPI: vllm

## Executive Summary

The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision `26587f9519e22a5c4549ead7595ad9ca3229c4fd`. It wraps serialized prompt-embedding reconstruction and dense conversion in `torch.sparse.check_sparse_tensor_invariants()`, but PyTorch 2.11.0 implements that context with save/enable/restore operations over process-global state. Two prompt-embedding parts in one `/v1/chat/completions` request are gathered concurrently on the event loop's default executor. When one context exits before the other loads its tensor, it can restore the global flag to `False` while the second part remains inside its guard.

In a deterministic run against hash-verified source from the affected revision, the actual target loader rejected an invalid sparse payload as a negative control. The frozen chat tracker then scheduled benign and malicious parts on distinct `asyncio_0` and `asyncio_1` threads. The benign context exited, the malicious loader observed the invariant flag disabled, and `torch.load(weights_only=True)` reconstructed indices `[[10], [10]]` for a declared shape of `[3, 3]`. The run intercepted the target's `to_dense()` call before it operated on the invalid tensor.

This primary trigger requires `--enable-prompt-embeds`, which is default-off, but it does **not** require `renderer_num_workers > 1`, a multimodal model, or `--enable-mm-embeds`. API authentication is optional in the stock server: middleware is installed only when CLI or environment…

Most recent entries from all

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

GHSA-pr7f-p5mw-fc87 — vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts