CVE-2026-73557 json
vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
published 2026-08-13 2 mo ago modified 2026-10-15 24 d ago also EUVD-2026-58064 , GHSA-pr7f-p5mw-fc87 , PYSEC-2026-3938
- cvss
- 5.3
- version 3.1, NVD
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 16%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- pypi vllm 0.26.0
- vllm-project vllm 0.26.0
- github.com/vllm-project/vllm@793cf79 commit
- github.com/vllm-project/vllm#48583 pull request
- github.com/vllm-project/vllm/releases/tag/v0.26.0 release
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-73557 updated cvss 5.3
vllm: vLLM: Incomplete remediation allows bypass via concurrent prompt processing
-
Red Hat AI Inference Server 3.5 rhaii/vllm-cpu-rhel9 1791473614, rhaii/vllm-cuda-rhel9 1791473631, rhaii/vllm-rocm-rhel9 1791425869, rhaii/vllm-gaudi-rhel9 1791427182, rhaii/vllm-spyre-rhel9 1791818357fixed: vendor fix RHSA-2026:82415
-
Red Hat Enterprise Linux AI 3.5 rhelai3/bootc-cuda-rhel9 1793135861, rhelai3/bootc-rocm-rhel9 1793135863, rhelai3/bootc-aws-cuda-rhel9 1793194817, rhelai3/bootc-gcp-cuda-rhel9 1793194815, rhelai3/disk-image-cuda-rhel9 1793206758, rhelai3/bootc-azure-cuda-rhel9 1793194815, +1 morefixed: vendor fix RHSA-2026:92452
-
Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9, rhaii/vllm-neuron-rhel9, +2 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9not affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 mo ago
Exploit prediction
0.25% chance of exploitation in the next 30 days, higher than 16% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.3 | 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 |
| CNA | 4.0 | 6.3 | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| NVD | 3.1 | 5.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | >=0.21.0, <0.26.0 |
0.26.0 |
Affected products
- vllm-project vllm
Classification
- Weakness
-
- CWE-362 Concurrent Execution using Shared Resource with Improper Synchronization
References
-
github.com
/vllm-project/vllm/pull/48583
web, issue-tracking, patch
-
github.com
/vllm-project/vllm/commit/793cf79c89d4049124e756915468ac30318f2e50
web, patch
-
github.com
/vllm-project/vllm/security/advisories/GHSA-pr7f-p5mw-fc87
web, mitigation, vendor-advisory
-
github.com
/vllm-project/vllm/releases/tag/v0.26.0
web, release-notes
-
nvd.nist.gov
/vuln/detail/CVE-2026-73557
advisory
-
github.com
/vllm-project/vllm
package
-
pypi.org
/project/vllm
package
-
github.com
/advisories/GHSA-pr7f-p5mw-fc87
advisory
Sources
- CVE List CVE-2026-73557
- GitHub Advisory GHSA-pr7f-p5mw-fc87
- NVD CVE-2026-73557
- OSV PYSEC-2026-3938
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.