GPU VulnDB

Database/AI/ML frameworks & serving

SGLang (`/update_weights_from_tensor`): Unsafe deserialization of the `serialized_named_tensors` argument

CVE-2025-10164AI/ML frameworks & servingcurated

Impact

Unsafe deserialization of the serialized_named_tensors argument

Who can reach it

Network to the SGLang HTTP API

What to do

Upgrade past 0.4.6; the weight-update endpoint must not be tenant-reachable

Fleet impact

How widespread

Very common - SGLang is the main vLLM alternative for high-throughput LLM serving on neoclouds; affects 0.4.6 through <0.5.4

Cost to remediate

daemon-restart - upgrade to 0.5.4+ and roll every serving replica

Why it hits the whole fleet

update_weights_from_tensor pickle-deserializes attacker input with no authentication, giving unauthenticated remote code execution on every SGLang serving process reachable on the network

References

This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.