TurboQuant KV cache compression for vLLM — fused Triton kernels, 3.76x compression, 3.7x faster decode on RTX 4090
Apache-2.0
All Versions
Vulnerabilities (Public)
Known vulnerabilities and security issues detected in the extension's dependencies and code.
No vulnerabilities found for this package.
Safety Discovered Vulnerabilities
Additional security issues found by Safety, exclusive to our platform.