CVE Feed

    Dashboard / CVE / CVE-2026-73557

    CVE-2026-73557

    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.

    Published:Aug 13, 2026
    Last Modified:Aug 13, 2026
    EPS:Aug 13, 2026
    EPSS Score:
    CVSS Score:6.3

    Affected Products

    Vendor
    Vllm-project
    Product
    Vllm

    Exploits

    No exploit reference

    Related CVEs

    CVE-2026-37237 (CVSS 7.5) — vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. Th…
    CVE-2026-73560 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalPr…
    CVE-2026-71486 (CVSS 4.3) — vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derend…
    CVE-2026-73559 (CVSS 6.5) — vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completio…
    CVE-2026-73558 (CVSS 5.3) — vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blo…
    CVE-2026-73556 (CVSS 5.3) — vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.reg…
    CVE-2026-73555 (CVSS 5.3) — vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_h…
    CVE-2026-55514 (CVSS 7.1) — vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds pa…
    CVE-2026-55574 (CVSS 8.7) — vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the str…
    CVE-2026-54234 (CVSS 7.5) — vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a front…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High