CVE-2025-62164

HIGHPre-NVD 8.88.8
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to the CVSS score beside it.

This high-severity CVE scores 8.8 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.9% (59th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from a secondary CVSS source
Sources: EPSS, a secondary CVSS source
8.8EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.9%CVSS: 8.8Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

CVSS v3
8.8
EG Score
8.8HIGHmedium confidence
EG Risk
40
EG Risk 40/100

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed (value × EchelonGraph’s weight)
Severity88% × 45%
The EG Score, 8.8 of 10.
Exploitation0.9% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
0.9%
EPSS %ILE
59th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

November 21, 2025

Last Modified

June 17, 2026

Advisory Details (3)

Auto-updated Aug 8, 2026
Patch available. Sources: github, github_commit, github_pr.
GitHub advisoryMentions a patch (unverified)

prompt_embeds deserialization allows DoS and potential RCE · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-mrw7-hf4f-83pf
GitHub pull request

[Frontend] Require flag for loading text and image embeds

Fix merged in vllm-project/vllm PR #27204 on 2025-10-22 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/27204
GitHub commit

commit 58fab50d8283 (vllm-project/vllm)

Fix landed in vllm-project/vllm commit 58fab50d8283 — awaiting tagged release

https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b

Vendor Advisories for CVE-2025-62164(11)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Patch Availability(10)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhaiis/vllm-spyre-rhel9:17823529192026-06-25redhat
redhatrhoai/odh-vllm-cpu-rhel9:17782643632026-05-20redhat
redhatrhoai/odh-vllm-gaudi-rhel9:17709560342026-03-04redhat
redhatrhaiis/vllm-cuda-rhel9:17721605932026-02-27redhat
redhatrhaiis/vllm-rocm-rhel9:17721606252026-02-27redhat
redhatrhoai/odh-kserve-storage-initializer-rhel9:v2.25.1-17653265132025-12-17redhat
redhatrhaiis/vllm-rocm-rhel9:3.2.5-17655526032025-12-17redhat
redhatrhaiis/vllm-cuda-rhel9:3.2.5-17655525802025-12-15redhat
redhatrhaiis/vllm-rocm-rhel9:3.2.5-17653611802025-12-15redhat
redhatrhaiis/vllm-tpu-rhel9:3.2.5-17655526192025-12-15redhat

Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
vllm0.10.2, 0.11.0
  • 0.10.2 up to 0.11.1: fixed in 0.11.1
—

Weakness Classification(4)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 11× in last 7d / 30× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 91 of 172 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 9 repeat rows among the latest 100 are merged into the row they repeat. The 81 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-15 16:31 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  2. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  3. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  4. 2026-10-12 16:51 UTCEG score recompute
  5. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  6. 2026-10-11 20:26 UTCEG score recompute
  7. 2026-10-11 18:37 UTCEG score recompute
  8. 2026-10-11 15:12 UTCEG score recompute
  9. 2026-10-11 13:47 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  10. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  11. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  12. 2026-10-08 17:10 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  13. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  14. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  15. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  16. 2026-10-04 23:21 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  17. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  18. 2026-10-01 19:49 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  19. 2026-10-01 11:40 UTCOSV refresh
  20. 2026-09-30 15:02 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  21. 2026-09-29 15:20 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  22. 2026-09-28 13:50 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  23. 2026-09-26 15:58 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  24. 2026-09-24 14:02 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  25. 2026-09-23 13:47 UTCEPSS rescoreEPSS 0.9% · 57th percentile
Show 66 more
  1. 2026-09-20 20:15 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  2. 2026-09-19 15:42 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  3. 2026-09-18 19:27 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  4. 2026-09-17 19:30 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  5. 2026-09-16 14:07 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  6. 2026-09-15 03:10 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  7. 2026-09-13 16:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  8. 2026-09-12 15:00 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  9. 2026-09-12 10:40 UTCOSV refresh
  10. 2026-09-11 14:52 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  11. 2026-09-11 09:36 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  12. 2026-09-10 09:34 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  13. 2026-09-08 22:00 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  14. 2026-09-07 16:00 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  15. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  16. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  17. 2026-09-02 14:11 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  18. 2026-09-01 13:53 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  19. 2026-08-30 19:16 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  20. 2026-08-30 01:21 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  21. 2026-08-28 21:40 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  22. 2026-08-27 14:24 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  23. 2026-08-26 14:45 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  24. 2026-08-25 13:48 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  25. 2026-08-24 15:33 UTCOSV refresh
  26. 2026-08-24 14:16 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  27. 2026-08-23 00:18 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  28. 2026-08-21 23:48 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  29. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  30. 2026-08-19 17:03 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  31. 2026-08-18 13:47 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  32. 2026-08-17 13:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  33. 2026-08-16 14:55 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  34. 2026-08-16 02:13 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  35. 2026-08-15 01:29 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  36. 2026-08-13 21:59 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  37. 2026-08-12 13:50 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  38. 2026-08-11 13:42 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  39. 2026-08-10 23:59 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  40. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  41. 2026-08-08 16:36 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  42. 2026-08-08 09:54 UTCEG score recompute
  43. 2026-08-08 09:54 UTCVendor advisory
  44. 2026-08-07 16:26 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  45. 2026-08-06 13:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  46. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  47. 2026-08-04 15:09 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  48. 2026-08-04 10:37 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  49. 2026-08-03 10:35 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  50. 2026-08-02 02:26 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  51. 2026-08-01 04:15 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  52. 2026-07-30 16:27 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  53. 2026-07-30 01:30 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  54. 2026-07-28 15:35 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  55. 2026-07-27 14:12 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  56. 2026-07-26 14:54 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  57. 2026-07-25 14:17 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  58. 2026-07-24 14:17 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  59. 2026-07-23 15:11 UTCOSV refresh
  60. 2026-07-23 14:18 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  61. 2026-07-23 03:00 UTCEG score recompute
  62. 2026-07-22 14:08 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  63. 2026-07-21 15:24 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  64. 2026-07-20 17:08 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  65. 2026-07-19 14:30 UTCEPSS rescoreEPSS 0.9% · 56th percentile
  66. 2026-07-19 02:28 UTCEPSS rescoreEPSS 0.8% · 54th percentile

Related CVEs(same product + same vendor + same CWE)

Frequently asked(5)

What is CVE-2025-62164?
CVE-2025-62164 is a high-severity vulnerability; its CVE record was published on November 21, 2025. vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing…
When was the CVE record for CVE-2025-62164 published?
The CVE record for CVE-2025-62164 was published on November 21, 2025. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of June 17, 2026; the record at its source may have been updated since.
Is CVE-2025-62164 actively exploited?
CVE-2025-62164 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.9% probability of exploitation in the next 30 days (59th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2025-62164?
CVE-2025-62164 has a CVSS base score of 8.8 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2025-62164?
A fix for CVE-2025-62164 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2025-62164 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2025-62164

Explore →

Is Your Infrastructure Affected by CVE-2025-62164?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs