3 matches found
Deserialization of Untrusted Data
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Deserialization of Untrusted Data in the shared-memory multimodal cache handle mechanism, where handles passed between processes via...
vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the mirrored sender/receiver cache protocol reaches. Summary vLLM's default multimodal cache...
GHSA-PH3R-5JFG-F84F vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the mirrored sender/receiver cache protocol reaches. Summary vLLM's default multimodal cache...