CVE-2026-34756

MEDIUMPre-NVD 6.56.5
EchelonGraph scoreMEDIUM confidence

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

This medium-severity CVE scores 6.5 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.4% (36th 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

Also known asEUVD-2026-19351 (ENISA EUVD) · GHSA-3mwp-wvh9-7528 (GitHub Security Advisories)Source: ENISA EUVD

6.5EG
EchelonGraph verdictMonitorRemediate within your standard update timelines (the SSVC decision on this page).
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 6.5Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

CVSS v3
6.5
EG Score
6.5MEDIUMmedium confidence
EG Risk
30
EG Risk 30/100

EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity65% × 45%
Impact severity (EG Severity): CVSS 6.5 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation0.8% × 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 every mission impact level.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (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
0.4%
EPSS %ILE
36th
KEV
Not listed

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (6.5): severity, escalated by confirmed exploitation. This CVE's 6.5 is its impact severity (EG Severity), not escalated.

EG Severity
6.5 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.a secondary CVSS source · CVSS v3.0 or v3.1
EG Likelihood
0.4% within 30 daysSource: FIRST EPSS. FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at every mission impact level.CISA BOD 26-04: 60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source: the SSVC and BOD 26-04 blocks below.

SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.

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

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (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)60 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 partial (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

April 6, 2026

Last Modified

August 25, 2026

Advisory Details (8)

Auto-updated Jul 7, 2026
Patch available. Sources: github, redhat, github_commit, github_pr.
Red Hat

2455425 – (CVE-2026-34756) CVE-2026-34756 vllm: vLLM: Denial of Service via excessively large 'n' parameter in OpenAI-compatible API

https://bugzilla.redhat.com/show_bug.cgi?id=2455425
Red HatMentions a patch (unverified)

cve-details

https://access.redhat.com/security/cve/CVE-2026-34756
Red HatMentions a patch (unverified)
https://access.redhat.com/errata/RHSA-2026:36006
Red HatMentions a patch (unverified)
https://access.redhat.com/errata/RHSA-2026:36005
GitHub advisoryMentions a patch (unverified)

OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528
GitHub pull request

fix(security): Add VLLM_MAX_N_SEQUENCES environment variable and enforce limit

Fix merged in vllm-project/vllm PR #37952 on 2026-03-27 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/37952
GitHub commit

commit b111f8a61f10 (vllm-project/vllm)

Fix landed in vllm-project/vllm commit b111f8a61f10 — awaiting tagged release

https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380

Patch Availability(8)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhelai3/disk-image-cuda-rhel9:17873107172026-08-24redhat
redhatrhelai3/bootc-rocm-rhel9:17872440062026-08-24redhat
redhatrhaii/vllm-rocm-rhel9:17871517742026-08-20redhat
redhatrhaii/vllm-spyre-rhel9:17871518402026-08-20redhat
redhatrhaii/vllm-cuda-rhel9:17871517712026-08-20redhat
redhatrhaii/vllm-cpu-rhel9:17871517692026-08-20redhat
redhatrhaiis/vllm-rocm-rhel9:17829512442026-07-06redhat
redhatrhaiis/vllm-cuda-rhel9:17829510122026-07-06redhat

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
vllm0.1.0 ... 0.9.2 (79 versions)
  • 0.1.0 up to 0.19.0: fixed in 0.19.0
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 8× in last 7d / 37× 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 99 of 227 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. 1 repeat row among the latest 100 is merged into the row it repeats. The 128 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  2. 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  3. 2026-10-27 16:31 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  4. 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  5. 2026-10-25 16:32 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  6. 2026-10-25 14:33 UTCEG score recompute
  7. 2026-10-24 16:32 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  8. 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  9. 2026-10-23 03:18 UTCEG score recompute
  10. 2026-10-23 03:18 UTCVendor advisory
  11. 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.8% · 55th percentile
  12. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  13. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  14. 2026-10-19 16:31 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  15. 2026-10-18 16:31 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  16. 2026-10-18 03:45 UTCEG score recompute
  17. 2026-10-17 16:34 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  18. 2026-10-16 16:41 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  19. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  20. 2026-10-14 16:32 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  21. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  22. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  23. 2026-10-12 16:12 UTCEG score recompute
  24. 2026-10-11 19:54 UTCEG score recompute
  25. 2026-10-11 17:07 UTCEG score recompute
Show 74 more
  1. 2026-10-11 14:34 UTCEG score recompute
  2. 2026-10-11 13:48 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  3. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  4. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  5. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  6. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  7. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.8% · 54th percentile
  8. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  9. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  10. 2026-10-02 13:41 UTCOSV refresh
  11. 2026-10-01 19:49 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  12. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  13. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  14. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  15. 2026-09-26 15:58 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  16. 2026-09-26 00:26 UTCEPSS rescoreEPSS 0.8% · 53rd percentile
  17. 2026-09-20 20:15 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  18. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  19. 2026-09-17 19:30 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  20. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  21. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  22. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  23. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  24. 2026-09-13 11:54 UTCOSV refresh
  25. 2026-09-12 15:01 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  26. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  27. 2026-09-11 09:37 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  28. 2026-09-10 09:34 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  29. 2026-09-08 22:00 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  30. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  31. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  32. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  33. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  34. 2026-09-01 13:53 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  35. 2026-09-01 04:39 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  36. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  37. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  38. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  39. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  40. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  41. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.4% · 33rd percentile
  42. 2026-08-25 13:25 UTCEG score recompute
  43. 2026-08-25 13:25 UTCVendor advisory
  44. 2026-08-25 12:22 UTCEG score recompute
  45. 2026-08-25 12:22 UTCVendor advisory
  46. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  47. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  48. 2026-08-21 13:22 UTCEG score recompute
  49. 2026-08-21 13:22 UTCVendor advisory
  50. 2026-08-21 12:32 UTCEG score recompute
  51. 2026-08-21 12:32 UTCVendor advisory
  52. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  53. 2026-08-20 13:59 UTCEG score recompute
  54. 2026-08-20 13:59 UTCVendor advisory
  55. 2026-08-20 12:45 UTCEG score recompute
  56. 2026-08-20 12:45 UTCVendor advisory
  57. 2026-08-19 17:03 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  58. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  59. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  60. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  61. 2026-08-16 08:24 UTCEG score recompute
  62. 2026-08-16 08:24 UTCVendor advisory
  63. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  64. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  65. 2026-08-14 05:33 UTCEG score recompute
  66. 2026-08-14 05:33 UTCVendor advisory
  67. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  68. 2026-08-12 19:47 UTCEG score recompute
  69. 2026-08-12 19:47 UTCVendor advisory
  70. 2026-08-12 13:50 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  71. 2026-08-11 04:30 UTCEG score recompute
  72. 2026-08-11 04:30 UTCVendor advisory
  73. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  74. 2026-08-10 04:46 UTCEG score recompute

Frequently asked(5)

What is CVE-2026-34756?
CVE-2026-34756 is a medium-severity vulnerability; its CVE record was published on April 6, 2026. vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and…
When was the CVE record for CVE-2026-34756 published?
The CVE record for CVE-2026-34756 was published on April 6, 2026. 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 August 25, 2026; the record at its source may have been updated since.
Is CVE-2026-34756 actively exploited?
CVE-2026-34756 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (36th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-34756?
CVE-2026-34756 has a CVSS base score of 6.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-34756?
A fix for CVE-2026-34756 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-34756 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-2026-34756

Explore →

Is Your Infrastructure Affected by CVE-2026-34756?

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