Answer in brief
CVE-2026-73557 records a Unknown severity vulnerability in vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| vllm-project/vllmgeneric | >= 0.20.2rc0, < 0.26.0 | Not reported |
Published upstream
Aug 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 13, 2026
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.
Quoted source text, attributed separately from HOL analysis.
Answer in brief
CVE-2026-73557 records a Unknown severity vulnerability in vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps vllm-project/vllm (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| vllm-project/vllmgeneric | >= 0.20.2rc0, < 0.26.0 | Not reported |
Published upstream
Aug 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 13, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 13, 2026
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.
Quoted source text, attributed separately from HOL analysis.