SUSE CVE-2026-102634

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

CVE-2026-102634

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

CVE-2026-102634 SGLang through 0.5.20 Denial of Service via Duplicate bootstrap_room

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

CVE-2026-102634 SGLang through 0.5.20 Denial of Service via Duplicate bootstrap_room

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

EUVD-2026-89029

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

CVE-2026-102634

SGLang versions through 0.5.20 are vulnerable to a Denial of Service (DoS) when running in prefill/decode disaggregation mode with the Mooncake KV transfer backend . The root cause is a failure to validate duplicate bootstrap_room fields in /generate requests. An unauthenticated attacker can expl...

CVE-2026-102634: Use of Multiple Resources with Duplicate Identifier

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstraproom fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent requests with identical bootstraproom values to crash scheduler processes or hang oth...

PT-2026-102682

Name of the Vulnerable Software and Affected Versions SGLang versions prior to 0.5.21 Description When operating in prefill/decode disaggregation mode with the Mooncake KV transfer backend, the software fails to validate duplicate bootstrap room fields in the '/generate' endpoint. Unauthenticated...

SUSE CVE-2026-94627

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts,...

CVE-2026-94625

A flaw was found in vLLM. A remote attacker can exploit this vulnerability by sending rejected prefill requests to the MooncakeConnector. This action creates ownerless transfer placeholders that are not properly reclaimed, leading to resource exhaustion. Consequently, legitimate requests may...

SUSE CVE-2026-93688

SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstraproom values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach the decode engine's POST /generate endpoint and submit arbitrary bootstraproom...

SUSE CVE-2026-93838

SGLang versions through 0.5.20 contain an unbounded memory allocation vulnerability in handlestagingreq that fails to validate chunkidx from ZMQ STAGINGREQ frames in prefill/decode disaggregation deployments. Attackers with access to the decode engine's internal ZMQ rank port can send a frame wit...

EUVD-2026-84219

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 4...

Reachable Assertion

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via an assertion failure in NixlBaseConnectorWorker.applyprefixcaching, which fails to properly validate block counts across...

PYSEC-2026-4005

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in...

CVE-2026-94625

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 4...

PYSEC-2026-4007

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 4...

PYSEC-2026-4007

vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can send rejected requests to exhaust sender task pools, causing valid requests to be delayed by up to 4...

PYSEC-2026-4004

vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomplete kvtransferparams dictionary entries to trigger an uncaught KeyError in EngineCore scheduling,...

CVE-2026-94627 vLLM through 0.29.0 GPU KV Cache Leak via Mooncake Transfer ID Collision

vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child requests share a single transfer ID in prefill/decode disaggregated deployments. Attackers can trigger GPU memory exhaustion by submitting completion requests with multiple prompts,...