Skip to content
HighVulnerabilityLLM-specific

CVE-2026-73557: vLLM race condition bypasses sparse tensor validation in prompt_embeds

Identifier
CVE-2026-73557
Published
Record updated
View JSON
Affected
  • vllm >= 0.21.0, < 0.26.0
Fixed in
0.26.0
  • released July 25, 2026, 19 days before disclosure
Known exploitation
Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS
0.2%

Summary

vLLM, an inference and serving engine for large language models, contains a flaw from 0.20.2rc0 through 0.26.0 in safe_load_prompt_embeds in vllm/renderers/embed_utils.py. The function toggles the process-global torch.sparse.check_sparse_tensor_invariants setting, and concurrent prompt_embeds parts submitted to POST /v1/chat/completions can race that state, letting an invalid sparse tensor reach tensor.to_dense despite the CVE-2025-62164 guard when enable_prompt_embeds is enabled.

Mitigation

This issue is fixed in version 0.26.0.